© 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 - 65k
    9. 16-GEMMASCOPE-RES-65K
    11. 31889
    Prev
    Next
    INDEX
    Explanations

    references to criminal record management and biometric data

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    criminal record databases and registries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    坞
    -0.62
    ValueStyle
    -0.59
     consultato
    -0.56
    ärä
    -0.55
    bewerken
    -0.52
     Yarm
    -0.50
    newtheorem
    -0.49
    Verlag
    -0.49
     Chapelle
    -0.48
    BagConstraints
    -0.47
    POSITIVE LOGITS
     database
    0.98
     databases
    0.93
     registry
    0.81
     registration
    0.75
    richTextPanel
    0.72
     electronic
    0.71
     Database
    0.70
     registers
    0.70
     computerized
    0.69
     register
    0.69
    Activations Density 0.150%

    No Known Activations