Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 4138
    Prev
    Next
    INDEX
    Explanations

    references to the term "Christian" and related concepts

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

    Tokens appearing after "Christian"

    np_acts-logits-general · gemini-2.0-flash

    Christian names and titles

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    ppuden
    -0.49
    InSection
    -0.48
     GeoNames
    -0.48
    GetKeyDown
    -0.48
     GreatSchools
    -0.45
    atschappij
    -0.45
    :)
    -0.45
     Notices
    -0.44
     tamen
    -0.44
     Tsche
    -0.43
    POSITIVE LOGITS
    ized
    0.70
    guarded
    0.69
    ization
    0.67
     nahilalakip
    0.66
     ControllerBase
    0.65
     cref
    0.63
    GraphicsUnit
    0.62
    aarrggbb
    0.61
    ised
    0.60
     Dior
    0.60
    Activations Density 0.045%

    No Known Activations