[cacio-e-pepe]

> So we did mechanistic studies on small models, Gemma 4 particularly, and found the hidden state for different layers carry meaningful self-awareness signal for various situations.

Neat! Just to make sure I understand - you trained your probe layer to take this hidden state and predict p(wrong)?

Curious to learn more. Any more info on your approach (esp the mechanistic study)?

[HenryNdubuaku]

Correct, the study is verbose, we will compile into a neat shareable report and publish once we solve the pending caveats. Interesting username btw haha.

[cacio-e-pepe]

Nice, looking forward to the report.

And thanks, huge pasta fan :)

[HenryNdubuaku]

anytime!