© 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. 9-GEMMASCOPE-RES-131K
    11. 13757
    Prev
    Next
    INDEX
    Explanations

    terms related to antibodies and their classifications

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

    clonal antibody

    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
     Infór
    -0.45
    IContainer
    -0.44
     aguja
    -0.43
     cooperación
    -0.43
    <?
    -0.42
     cartera
    -0.42
     keber
    -0.42
     gobern
    -0.41
     peines
    -0.40
     presidenta
    -0.38
    POSITIVE LOGITS
    Chooser
    1.09
    clonal
    0.93
    AutoresizingMask
    0.91
     nowrap
    0.90
    unwrap
    0.88
    nowrap
    0.74
     Saratoga
    0.66
    chooser
    0.64
    complexType
    0.63
    zzleHttp
    0.58
    Activations Density 0.003%

    No Known Activations