© 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. 20-GEMMASCOPE-RES-65K
    11. 3667
    Prev
    Next
    INDEX
    Explanations

    elements related to personal or contact information in transactional contexts

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

    addresses and email addresses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    Not in Any Lists

    No Comments

    Negative Logits
    protoimpl
    -0.47
    simpleType
    -0.45
    init
    -0.44
     Vikipedi
    -0.43
    }{|
    -0.42
    Становништво
    -0.41
    Ini
    -0.41
     rotation
    -0.41
     fla
    -0.40
    vège
    -0.40
    POSITIVE LOGITS
     address
    2.82
     addresses
    2.49
     Address
    2.45
    address
    2.39
     ADDRESS
    2.30
     Addresses
    2.19
    Address
    2.18
     adress
    2.09
    ADDRESS
    2.05
    addresses
    1.95
    Activations Density 0.218%

    No Known Activations