© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 14666
    Prev
    Next
    INDEX
    Explanations

    comments in the code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 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
    ftagPool
    -0.88
     MainAxisSize
    -0.82
    出版年
    -0.81
     للمعارف
    -0.77
    躇
    -0.75
    contentLoaded
    -0.71
    tvguidetime
    -0.70
    PreferredItem
    -0.68
    postIndex
    -0.67
     Мексичка
    -0.66
    POSITIVE LOGITS
    //
    1.40
     //
    1.13
    //
    1.10
    {//
    0.90
    );//
    0.90
    ;//
    0.88
     {//
    0.88
    )//
    0.87
    ){//
    0.82
    ////
    0.82
    Activations Density 0.073%

    No Known Activations