© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 4-GEMMASCOPE-RES-16K
    11. 1241
    Prev
    Next
    INDEX
    Explanations

    concepts related to measurements and correlations in scientific research

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    :✨
    -1.02
     MainAxisSize
    -0.75
    enumi
    -0.71
     groupBox
    -0.70
    gheny
    -0.67
    ofern
    -0.66
    Демографія
    -0.66
    atorship
    -0.66
     phiếu
    -0.65
     SOCK
    -0.65
    POSITIVE LOGITS
     to
    1.09
     thereto
    0.92
     acesso
    0.86
    ToAdd
    0.78
     accès
    0.76
     accéder
    0.76
    Assignable
    0.76
     attaches
    0.76
     acceder
    0.75
     vistazo
    0.73
    Activations Density 1.455%

    No Known Activations