© 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. 34951
    Prev
    Next
    INDEX
    Explanations

    HTML table elements and their attributes

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

    html table header field

    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
     dedans
    -0.49
     dessus
    -0.48
    .
    -0.46
     répertoire
    -0.46
    ,
    -0.38
     Gegenteil
    -0.35
     nôtre
    -0.35
    ->
    -0.35
     netts
    -0.35
     vôtre
    -0.34
    POSITIVE LOGITS
    ReusableCell
    0.76
    HostException
    0.75
    HtmlAttribute
    0.73
    AnchorStyles
    0.71
     Signalez
    0.71
     Infórmanos
    0.70
    LEncoder
    0.69
    ########.
    0.67
    voix
    0.66
    bootstrapcdn
    0.65
    Activations Density 0.002%

    No Known Activations