© 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. 21-GEMMASCOPE-RES-16K
    11. 9855
    Prev
    Next
    INDEX
    Explanations

    references to immune defense mechanisms and protective measures against pathogens

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    ⓧ
    -0.56
     GeoNames
    -0.54
    mények
    -0.50
    moveToFirst
    -0.49
    ArgsConstructor
    -0.46
     percolation
    -0.43
    khana
    -0.41
    writeFieldEnd
    -0.41
    roek
    -0.41
     hài
    -0.41
    POSITIVE LOGITS
     protection
    3.11
     Protection
    2.65
    protection
    2.64
     protecting
    2.63
     protect
    2.62
    Protection
    2.55
     protective
    2.46
     protects
    2.45
     PROTECTION
    2.40
     Protect
    2.38
    Activations Density 0.756%

    No Known Activations