© 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. 20-GEMMASCOPE-RES-131K
    11. 78758
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "data" in various contexts

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

    data, dataclasses, datalayer

    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
     myſelf
    -0.52
    UrlResolution
    -0.52
     dalamnya
    -0.52
    antaranya
    -0.51
    Cliquez
    -0.49
     antaranya
    -0.48
     startIndex
    -0.48
    iii
    -0.48
     Verpflich
    -0.47
    ever
    -0.47
    POSITIVE LOGITS
     Dat
    1.05
     DAT
    0.99
    Dat
    0.99
     dat
    0.97
    dat
    0.96
     Data
    0.94
    DAT
    0.93
     DATA
    0.90
     Datas
    0.88
     data
    0.83
    Activations Density 0.005%

    No Known Activations