© 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. 30-GEMMASCOPE-RES-16K
    11. 15473
    Prev
    Next
    INDEX
    Explanations

    references to health and social support systems

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

    Follows a noun

    np_acts-logits-general · gemini-2.0-flash

    COVID pandemic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ModelExpression
    -0.40
     références
    -0.39
    毎回
    -0.35
    HtmlAttribute
    -0.32
     Glaub
    -0.31
    ılı
    -0.30
    success
    -0.30
    每年
    -0.29
    hadiran
    -0.29
    Success
    -0.29
    POSITIVE LOGITS
     COVID
    1.47
     Covid
    1.42
     covid
    1.41
    COVID
    1.38
    Covid
    1.37
    covid
    1.30
     coronavirus
    1.30
     pandemic
    1.23
     lockdown
    1.23
     Coronavirus
    1.22
    Activations Density 0.179%

    No Known Activations