Research · Per Ardua

Layer-Resolved Response Tensor: Where Domain Selectivity Lives in the Forward Pass

Mapping domain selectivity across the full depth of a transformer

AI-9 Activation Geometry DOI

Executive Summary

Paper VIII established the terminal measurement limit: shaped noise injected at the final transformer layers cannot achieve domain-selective entropy effects because nonlinear mixing at intermediate layers scrambles the signal. This paper asks a natural follow-up: where in the forward pass does domain selectivity actually live?

We map the full selectivity profile at nine sampled transformer layers in Qwen-2.5 7B (28 layers total), measuring where domain selectivity peaks and where it vanishes. The answer is a weak Outcome A: mean selectivity peaks at intermediate layers 7-10 (mean selectivity approximately 0.5) and declines toward both input and output layers. Absolute selectivity is modest at all layers.

Key Findings

  • Selectivity peaks at intermediate layers: Layers 7-10 show the highest domain selectivity (mean ~0.5), declining toward both input and output
  • Domain asymmetry: Code and science domains consistently exhibit positive selectivity; medical and legal exhibit negative selectivity across all layers
  • Modest absolute values: No layer achieves selectivity exceeding the concentration barrier bound of k/d_eff ~ 1.8
  • Consistent with Paper XI: The effective dimensionality constraint explains the selectivity profile without requiring additional mechanisms

Significance

This paper provides the spatial map that the subsequent papers (X-XII) explain. The finding that selectivity peaks at intermediate layers — not at the input where INLP directions are defined, and not at the output where effects are measured — is the first indication that the terminal measurement problem is not merely an output-layer phenomenon but reflects a structural property of the full forward pass.

Key References

  • McEntire (2026) — Shaped Noise Injection: the terminal measurement limit (Paper VIII)
  • McEntire (2026) — The Concentration Barrier: effective dimensionality bounds (Paper XI)
  • Ravfogel et al. (2020) — Iterative Nullspace Projection for domain direction identification

Download Full Paper

Access the complete research paper with detailed methodology, empirical evidence, and formal proofs.

Download PDF