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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 22-GEMMASCOPE-RES-16K
    6. 12964
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals and events, particularly within a community context

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

    Jewish names and titles

    np_acts-logits-general · gemini-2.0-flash

    Jewish religious figures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Datuak
    -0.70
    Xna
    -0.67
    躇
    -0.66
     الرياضيه
    -0.63
     Wikimedijinoj
    -0.58
    waan
    -0.56
     جغرافيا
    -0.55
    جغرافيا
    -0.54
     PDO
    -0.53
     içeris
    -0.53
    POSITIVE LOGITS
     Jewish
    0.77
     Goldstein
    0.73
     Shapiro
    0.72
     Rabbi
    0.68
     Baruch
    0.67
     Levy
    0.67
     Cohen
    0.67
     synagogue
    0.66
     Hyman
    0.65
     Goldberg
    0.64
    Activations Density 0.265%

    No Known Activations