© 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. 86553
    Prev
    Next
    INDEX
    Explanations

    numeric values and formatting details typically associated with data or code

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

    numbers followed by 'user' or 'Wed'

    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
     FetchType
    -0.73
     ThemeData
    -0.62
     MainAxisSize
    -0.59
     Wikimedijinoj
    -0.57
    AutoScaleMode
    -0.57
     '\\;'
    -0.56
    Спасылкі
    -0.54
     kaarangay
    -0.54
    djangoproject
    -0.54
    المكان
    -0.53
    POSITIVE LOGITS
     revision
    0.36
    Revision
    0.36
     Revision
    0.34
     last
    0.34
    NonNull
    0.31
     perbaikan
    0.31
    enterOuterAlt
    0.31
    attendre
    0.31
    Guard
    0.30
    setBorder
    0.30
    Activations Density 0.011%

    No Known Activations