Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 14430
    Prev
    Next
    INDEX
    Explanations

    programming languages and technical references within code-related content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+#
    -0.81
     AssemblyCulture
    -0.80
    bootstrapcdn
    -0.74
    IntoConstraints
    -0.73
    ніципалі
    -0.72
    NSIndexPath
    -0.69
    RenderAtEndOf
    -0.66
     Chwiliwch
    -0.66
    InjectAttribute
    -0.65
    RectangleBorder
    -0.64
    POSITIVE LOGITS
     JavaScript
    1.01
     Java
    0.95
     javascript
    0.94
     Python
    0.92
     java
    0.91
     python
    0.88
    JavaScript
    0.86
     Javascript
    0.85
    python
    0.84
    javascript
    0.84
    Activations Density 0.661%

    No Known Activations