© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 42682
    Prev
    Next
    INDEX
    Explanations

    proper nouns and names of individuals in a context related to roles or appointments

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    names and their roles

    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
    Negative Logits
    FetchType
    -0.32
     onBind
    -0.31
     handleMessage
    -0.30
    Démographie
    -0.28
     craze
    -0.27
    ற
    -0.26
     σω
    -0.26
    ฤษ
    -0.25
    struktion
    -0.25
    stufen
    -0.25
    POSITIVE LOGITS
    Parcelize
    0.63
    
    0.62
     queſta
    0.62
     transfieras
    0.61
    postmedia
    0.60
    évaluateur
    0.59
     تضيفلها
    0.59
    InputTagHelper
    0.58
    addPreferredGap
    0.58
     Expertise
    0.57
    Activations Density 0.021%

    No Known Activations