© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 104934
    Prev
    Next
    INDEX
    Explanations

    references to biometric identifiers, particularly fingerprints and DNA data

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    awtextra
    -0.49
    WriteLiteral
    -0.48
    */}
    -0.47
    --}}
    -0.46
    >--}}
    -0.45
     muligt
    -0.45
     noastră
    -0.45
     ArrayAdapter
    -0.44
    reactstrap
    -0.44
    verwijspagina
    -0.43
    POSITIVE LOGITS
     fingerprint
    1.03
     biometric
    0.93
     Fingerprint
    0.91
     fingerprints
    0.82
    fingerprint
    0.79
    Fingerprint
    0.78
     Finger
    0.56
     barcode
    0.55
    Autoritní
    0.54
     finger
    0.51
    Activations Density 0.014%

    No Known Activations