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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3617
    Prev
    Next
    INDEX
    Explanations

    quantities and frequency terms in discussions of scientific or statistical data

    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
    contentLoaded
    -0.58
    MigrationBuilder
    -0.55
    z
    -0.53
    ائج
    -0.52
    fortawesome
    -0.52
    зец
    -0.52
    total
    -0.50
     tenere
    -0.50
     bisogna
    -0.50
    rrggbb
    -0.50
    POSITIVE LOGITS
     ModelExpression
    0.86
    zości
    0.80
     plupart
    0.77
    XmlAccessorType
    0.74
     çoğu
    0.73
    anskje
    0.71
     maioria
    0.70
    principalTable
    0.70
     большин
    0.69
     meisten
    0.69
    Activations Density 0.344%

    No Known Activations