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 Post
    5. 12-GEMMASCOPE-RES-1M
    6. 49
    Prev
    Next
    INDEX
    Explanations

    references to utility functions or packages in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_1m/average_l0_107
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    1,048,576
    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
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    awtextra
    -0.85
     ModelExpression
    -0.82
    ⓧ
    -0.82
     nakalista
    -0.80
    styleType
    -0.78
     ویکی‌پدیای
    -0.76
    StoreMessageInfo
    -0.74
    SequentialGroup
    -0.73
     كومونز
    -0.69
    WriteBarrier
    -0.69
    POSITIVE LOGITS
    IContainer
    0.54
    !("{}",
    0.47
     MonoBehaviour
    0.46
    use
    0.44
    XmlType
    0.43
    USO
    0.42
    karl
    0.42
     Alcalde
    0.42
    ;';
    0.41
    ofstream
    0.40
    Activations Density 0.001%

    No Known Activations