> 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)?
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)?