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. 22-GEMMASCOPE-RES-16K
    6. 14045
    Prev
    Next
    INDEX
    Explanations

    code related to package and import statements in Java

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WriteAttribute
    -0.64
     ролях
    -0.56
    त्व
    -0.55
     CWE
    -0.52
    addCriterion
    -0.52
    Zunanje
    -0.50
    mlb
    -0.50
    vatar
    -0.49
    Xaml
    -0.48
    principalColumn
    -0.48
    POSITIVE LOGITS
     java
    0.91
     static
    0.82
     org
    0.71
     javax
    0.69
    import
    0.67
    triangleq
    0.64
    Datuak
    0.60
    RenderAtEndOf
    0.60
     android
    0.59
    }'.
    0.58
    Activations Density 0.021%

    No Known Activations