© 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. 53238
    Prev
    Next
    INDEX
    Explanations

    programming concepts and structures related to data management and processing

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

    data and specifications

    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
    awaiter
    -0.78
     AssemblyCompany
    -0.70
    цездатний
    -0.68
     Seeder
    -0.61
     feroit
    -0.60
    principalColumn
    -0.58
    ьаж
    -0.56
     smtplib
    -0.55
    transQ
    -0.54
    OGND
    -0.53
    POSITIVE LOGITS
    Parcelize
    0.36
    Embeddable
    0.36
    ApiModelProperty
    0.34
    ClInclude
    0.34
    toHave
    0.34
     createContext
    0.33
     mapStateToProps
    0.33
    Razor
    0.32
    usepackage
    0.31
     Came
    0.31
    Activations Density 0.350%

    No Known Activations