Neuronpedia
Get Started
API
Releases
Jump To
Search
Models
Assistant Axis
NEW
Circuit Tracer
NEW
Steer
SAE Evals
Exports
Community
Blog
Privacy & Terms
Contact
Sign In
© Neuronpedia 2026
Privacy & Terms
Blog
GitHub
Slack
Twitter
Contact
Home
Google DeepMind · Exploring Gemma 2 with Gemma Scope
Gemma-2-9B
Residual Stream - 16k
36-GEMMASCOPE-RES-16K
14687
Prev
Next
MODEL
36-gemmascope-res-16k
Source/SAE
INDEX
Go
Explanations
medical terminology related to depressive symptoms and pharmaceuticals
oai_token-act-pair · gpt-4o-mini
Triggered by @bot
No Scores
New Auto-Interp
AutoInterp Type
claude-4-5-haiku
Generate
Top Features by Cosine Similarity
Comparing With
GEMMA-2-9B @ 36-gemmascope-res-16k
Configuration
google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
How To Load
Prompts (Dashboard)
24,576 prompts, 128 tokens each
Dataset (Dashboard)
monology/pile-uncopyrighted
Features
16,384
Data Type
float32
Hook Name
blocks.36.hook_resid_post
Hook Layer
36
Architecture
jumprelu
Context Size
1,024
Dataset
monology/pile-uncopyrighted
Activation Function
relu
Show All
Embeds
Show Plots
Show Explanation
Show Activations
Show Test Field
Show Steer
Show Link
IFrame
<iframe src="https://www.neuronpedia.org/gemma-2-9b/36-gemmascope-res-16k/14687?embed=true&embedexplanation=true&embedplots=true&embedsteer=true&embedactivations=true&embedlink=true&embedtest=true" title="Neuronpedia" style="height: 300px; width: 540px;"></iframe>
Link
https://www.neuronpedia.org/gemma-2-9b/36-gemmascope-res-16k/14687?embed=true&embedexplanation=true&embedplots=true&embedsteer=true&embedactivations=true&embedlink=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Negative Logits
pleaſure
-1.20
ſta
-1.14
ſte
-1.14
ſei
-1.13
ſche
-1.10
ſch
-1.09
myſelf
-1.08
ſelves
-1.07
ſal
-1.06
ſelf
-1.02
POSITIVE LOGITS
l
0.47
t
0.46
com
0.45
l
0.45
t
0.44
v
0.44
r
0.43
n
0.43
re
0.42
proiect
0.42
Act
ivations
Density 1.225%
Stacked
Snippet
Full
Show Raw Tokens
Show Formatted
Show Breaks
Hide Breaks
No Known Activations
