© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 91026
    Prev
    Next
    INDEX
    Explanations

    keywords and structures related to database queries and responses

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

    listing next results

    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
     making
    -0.34
     Fest
    -0.32
    ignon
    -0.31
    运气
    -0.30
     cre
    -0.30
    jul
    -0.30
     lighting
    -0.30
    kelly
    -0.30
     curses
    -0.29
    道
    -0.29
    POSITIVE LOGITS
    請繼續往下閱讀
    0.77
     ModelExpression
    0.65
    :✨
    0.64
    ChildScrollView
    0.61
    脚注の使い方
    0.57
    toMatchSnapshot
    0.55
    
    0.54
     nahilalakip
    0.54
    pecabe
    0.53
     łóż
    0.53
    Activations Density 0.007%

    No Known Activations