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. 12-GEMMASCOPE-RES-16K
    6. 378
    Prev
    Next
    INDEX
    Explanations

    import statements related to the Apache Commons library

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 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
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    apimachinery
    -0.84
     GenerationType
    -0.79
     autorytatywna
    -0.78
    SerializedName
    -0.77
    ńczy
    -0.71
     通販
    -0.71
    /*
    -0.68
     &___
    -0.67
    jsii
    -0.67
    RunWith
    -0.67
    POSITIVE LOGITS
     Apache
    0.72
    commons
    0.69
    Apache
    0.66
    apache
    0.63
     apache
    0.61
     Friar
    0.56
    ترة
    0.55
    ხ
    0.55
    icoot
    0.55
     mosques
    0.55
    Activations Density 0.104%

    No Known Activations