© Neuronpedia 2026
Privacy & Terms
Blog
GitHub
Slack
Twitter
Contact
Neuronpedia
Jacobian Lens
NEW
Natural Language
Autoencoders
NEW
Assistant Axis
NEW
Circuit Tracer
UPDATE
Releases
Jump To
Search
Steer
SAE Evals
Exports
interp-engine
NEW
Guides
API
Community
Blog
Privacy & Terms
Contact
Sign In
Home
Google DeepMind · Exploring Gemma 2 with Gemma Scope
Gemma-2-9B
Residual Stream - 16k
12-GEMMASCOPE-RES-16K
4000
Prev
Next
MODEL
12-gemmascope-res-16k
Source/SAE
INDEX
Go
Explanations
the use of the word "of" in various contexts
oai_token-act-pair · gpt-4o-mini
Triggered by @bot
No Scores
the preposition "of" when it introduces a descriptive or possessive relationship, particularly in formal or technical contexts.
oai_token-act-pair · claude-4-5-sonnet
Triggered by @jyhe0408
No Scores
genitive or partitive prepositions that link nouns, including cross‑lingual variants (e.g., Romance equivalents).
oai_token-act-pair · gpt-5
Triggered by @jyhe0408
No Scores
New Auto-Interp
AutoInterp Type
claude-4-5-haiku
Generate
Top Features by Cosine Similarity
Comparing With
GEMMA-2-9B @ 12-gemmascope-res-16k
Configuration
google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
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.12.hook_resid_post
Hook Layer
12
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/12-gemmascope-res-16k/4000?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/12-gemmascope-res-16k/4000?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
faſt
-0.77
ſta
-0.74
juſ
-0.73
ſche
-0.70
raiſ
-0.70
viſ
-0.66
ſtand
-0.64
ſur
-0.62
houſe
-0.60
ſelf
-0.60
POSITIVE LOGITS
of
1.31
Of
1.05
of
1.05
OF
1.04
Of
0.98
của
0.87
ของ
0.79
OF
0.76
オブ
0.76
של
0.72
Act
ivations
Density 1.698%
Stacked
Snippet
Full
Show Breaks
Hide Breaks
No Known Activations