© 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. 9-GEMMASCOPE-RES-131K
    6. 84398
    Prev
    Next
    INDEX
    Explanations

    mentions of comments in various forms

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

    Comment and its continuations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DotNetBar
    -0.65
     Efq
    -0.51
     Majefty
    -0.50
     myſelf
    -0.50
    AspNetCore
    -0.50
    exa
    -0.48
    GI
    -0.47
     EG
    -0.47
    RG
    -0.47
    Ru
    -0.46
    POSITIVE LOGITS
    Comment
    1.73
     Comment
    1.73
    COMMENT
    1.27
    comment
    1.22
     COMMENT
    1.20
     comment
    0.85
     commentator
    0.79
     Commentary
    0.77
    Commentary
    0.72
    commentId
    0.71
    Activations Density 0.005%

    No Known Activations