© 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-2-2B
    7. Residual Stream - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 4071
    Prev
    Next
    INDEX
    Explanations

    keywords and identifiers related to programming and software development

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    Grá
    -0.68
    Abitanti
    -0.67
     Drapeau
    -0.62
     Мексичка
    -0.61
    JPL
    -0.58
    .'</
    -0.57
    becher
    -0.56
    ábado
    -0.56
    Général
    -0.56
    Controllo
    -0.55
    POSITIVE LOGITS
     Réponses
    0.66
    inn
    0.60
    inc
    0.56
     unt
    0.56
    hObject
    0.55
     يتيمه
    0.55
    CommonModule
    0.54
    uhnya
    0.53
    ild
    0.53
    NonNull
    0.53
    Activations Density 2.682%

    No Known Activations