© 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
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 104921
    Prev
    Next
    INDEX
    Explanations

    references to programming entities or structures related to command and data handling in coding frameworks

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
    __*/
    -0.58
     <=",
    -0.32
    RoutingModule
    -0.31
     dem
    -0.31
    ContentAsync
    -0.30
    ImageContext
    -0.28
    VIAF
    -0.28
    '}}>
    -0.27
    swire
    -0.26
    天神
    -0.26
    POSITIVE LOGITS
    PreInfinity
    1.00
     HFILL
    0.77
    stateProvider
    0.73
    IntoConstraints
    0.72
    NameInMap
    0.67
    adaptiveStyles
    0.66
    NewRow
    0.66
    DIPSETTING
    0.64
     disambiguazione
    0.63
    YYCURSOR
    0.61
    Activations Density 0.032%

    No Known Activations