© 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 - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 3095
    Prev
    Next
    INDEX
    Explanations

    code syntax related to control flow structures and function definitions

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    whitespace and indentation in code.

    oai_token-act-pair · claude-4-5-haiku
    Triggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    makeConstraints
    -0.65
    ISupport
    -0.55
    urably
    -0.52
    uisine
    -0.51
    urlpatterns
    -0.50
    ItemBackground
    -0.48
    ConstraintMaker
    -0.47
    istoitu
    -0.46
    Демографія
    -0.46
     Paglinawan
    -0.45
    POSITIVE LOGITS
     case
    0.43
    case
    0.42
     otherwise
    0.40
    GEBURTSDATUM
    0.37
    otherwise
    0.36
     Signalez
    0.36
    QMetaType
    0.36
    }
    0.35
    else
    0.35
     else
    0.35
    Activations Density 0.208%

    No Known Activations