© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 42484
    Prev
    Next
    INDEX
    Explanations

    prominent names and terms related to significant achievements, particularly in education and sports

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

    Marcus Rashford, Fulbright, FixedSize

    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
    IndentedString
    -0.60
    Derbyniad
    -0.58
    Cyfarwyddwr
    -0.58
    featureID
    -0.57
    VersionUID
    -0.56
    styleType
    -0.54
    TypedDataSet
    -0.54
     onBackPressed
    -0.54
     ilustracja
    -0.54
    eraard
    -0.54
    POSITIVE LOGITS
     Bauhaus
    0.46
    Portály
    0.45
     Fulbright
    0.44
    TableAdapter
    0.40
    AppUser
    0.39
    createNewFile
    0.38
     Canva
    0.37
    FixedSize
    0.36
    HSV
    0.36
    __;
    0.36
    Activations Density 0.007%

    No Known Activations