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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 98908
    Prev
    Next
    INDEX
    Explanations

    identifiers related to user accounts and permissions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    uid, TID, SID, lineage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     arşivlendi
    -0.80
    //
    -0.76
    CloseOperation
    -0.66
    клопе
    -0.61
    {
    
    
    -0.61
     {
    
    
    -0.60
    存于互联网档案馆
    -0.60
    MLLoader
    -0.60
    ỡng
    -0.59
    GroupLayout
    -0.57
    POSITIVE LOGITS
     uid
    0.94
    uid
    0.92
    getUid
    0.85
    Uid
    0.83
     UID
    0.79
    UID
    0.71
    uids
    0.56
    setUserId
    0.49
    id
    0.48
     Quid
    0.48
    Activations Density 0.011%

    No Known Activations