Neuronpedia
Get Started
API
Releases
Jump To
Search
Models
Circuit Tracer
NEW
Steer
SAE Evals
Blog
Slack
Privacy & Terms
Contact
Sign In
© Neuronpedia 2025
Privacy & Terms
Blog
GitHub
Slack
Twitter
Contact
Home
Google DeepMind · Exploring Gemma 2 with Gemma Scope
Gemma-2-2B
Residual Stream - 16k
18-GEMMASCOPE-RES-16K
10665
Prev
Next
MODEL
18-gemmascope-res-16k
Source/SAE
INDEX
Go
Explanations
technical jargon and specialized terms related to research and development
oai_token-act-pair · gpt-4o-mini
Triggered by @bot
No Scores
New Auto-Interp
AutoInterp Type
claude-3-5-haiku-20241022
Generate
Top Features by Cosine Similarity
Comparing With
GEMMA-2-2B @ 18-gemmascope-res-16k
Configuration
google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
How To Load
Prompts (Dashboard)
36,864 prompts, 128 tokens each
Dataset (Dashboard)
monology/pile-uncopyrighted
Features
16,384
Data Type
float32
Hook Name
blocks.18.hook_resid_post
Hook Layer
18
Architecture
jumprelu
Context Size
1,024
Dataset
monology/pile-uncopyrighted
Activation Function
relu
Show All
Embeds
Plots
Explanation
Show Test Field
Default Test Text
IFrame
<iframe src=https://www.neuronpedia.org/gemma-2-2b/18-gemmascope-res-16k/10665?embed=true&embedexplanation=true&embedplots=true&embedtest=true" title="Neuronpedia" style="height: 300px; width: 540px;"></iframe>
Link
https://www.neuronpedia.org/gemma-2-2b/18-gemmascope-res-16k/10665?embed=true&embedexplanation=true&embedplots=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Negative Logits
is
-1.03
was
-0.91
has
-0.75
does
-0.65
isn
-0.64
was
-0.62
darstellt
-0.62
Was
-0.61
Is
-0.60
hasn
-0.60
POSITIVE LOGITS
are
2.18
were
1.93
were
1.50
are
1.48
aren
1.48
weren
1.47
WERE
1.42
ARE
1.42
Were
1.30
Are
1.29
Act
ivations
Density 1.558%
Test
Steer
Stacked
Snippet
Full
Show Breaks
Hide Breaks
No Known Activations
