Neuronpedia
Get Started
API
Releases
Jump To
Search
Models
Circuit Tracer
NEW
Steer
SAE Evals
Exports
Slack
Blog
Privacy & Terms
Contact
Sign In
© Neuronpedia 2025
Privacy & Terms
Blog
GitHub
Slack
Twitter
Contact
Home
Joseph Bloom · Initial Gemma-2B-IT SAEs
Gemma-2B-IT
Residual Stream
12-RES-JB
16083
Prev
Next
MODEL
12-res-jb
Source/SAE
INDEX
Go
Explanations
mentions of legal issues or conflicts in a familial context
oai_token-act-pair · gpt-3.5-turbo
Triggered by @bot
No Scores
New Auto-Interp
AutoInterp Type
claude-4-5-haiku
Generate
Top Features by Cosine Similarity
Configuration
jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
How To Load
Prompts (Dashboard)
24,576 prompts, 128 tokens each
Dataset (Dashboard)
HuggingFaceFW/fineweb
Features
16,384
Data Type
float32
Hook Name
blocks.12.hook_resid_post
Hook Layer
12
Architecture
standard
Context Size
1,024
Dataset
Skylion007/openwebtext
Activation Function
relu
Show All
Embeds
Plots
Explanation
Show Test Field
Default Test Text
IFrame
<iframe src=https://www.neuronpedia.org/gemma-2b-it/12-res-jb/16083?embed=true&embedexplanation=true&embedplots=true&embedtest=true" title="Neuronpedia" style="height: 300px; width: 540px;"></iframe>
Link
https://www.neuronpedia.org/gemma-2b-it/12-res-jb/16083?embed=true&embedexplanation=true&embedplots=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Neuron Alignment
Index
Value
% of L₁
856
+0.17
0.5%
1343
+0.10
0.3%
764
+0.10
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
856
+0.17
0.04
2012
+0.10
0.04
776
+0.10
0.04
Negative Logits
fta
-1.22
thut
-1.14
ftu
-1.13
fte
-1.12
:,,
-1.06
»>
-1.05
ecru
-1.04
fup
-1.03
aen
-1.02
<^
-1.01
POSITIVE LOGITS
updated
0.55
updating
0.53
updating
0.52
update
0.50
updated
0.50
Updating
0.49
Updated
0.48
update
0.47
Updated
0.47
Updating
0.46
Act
ivations
Density 0.202%
Stacked
Snippet
Full
Show Raw Tokens
Show Formatted
Show Breaks
Hide Breaks
No Known Activations
