INDEX
Model
gemma-2-9b-it
Layer #
20
Steering Hook
blocks.20.hook_resid_pre
Steering Strength
43.25
Uploader
bot-neuronpedia
Created At
2/15/2025 1:06:43 AM
Raw Vector
Actions
Explanations
references to technical specifications or programming elements
New Auto-Interp
Negative Logits
-0.40
-
-0.36
(
-0.33
(
-0.32
)
-0.32
<eos>
-0.30
\
-0.30
really
-0.28
]
-0.27
↵
-0.27
POSITIVE LOGITS
rrggbb
1.04
<unused41>
0.85
<pad>
0.85
<unused8>
0.85
<unused14>
0.85
<unused23>
0.85
<unused28>
0.85
<unused51>
0.85
<unused52>
0.85
<unused74>
0.85
Activations Density 4.083%