claim
active
claim:gemma-represents-a-strong-ordering-of-interventions-in-activations-but-cannot-output-it-in-token-space-when-instructed

Gemma represents a strong ordering of interventions in activations but cannot output it in token space when instructed.

Interpretation of probe vs judge gap.

Source paper

extracted_from
Features as Rewards: Scalable Supervision for Open-Ended Tasks via Interpretability
(2026) · Aaditya Vikram Prasad · Connor Watts · Jack Merullo · Dhruvil Gala +3

Neighborhood — ranked by edge-count

Related by similarity (8)

cosine ≥ 0.65 · no typed edge

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.