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. 7897
    Prev
    Next
    INDEX
    Explanations

    HTML attributes and specific structural elements of a web page

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

    Two-letter language codes

    np_acts-logits-general · gemini-2.0-flash

    language codes

    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
    migrationBuilder
    -0.96
     ExecuteAsync
    -0.90
    MigrationBuilder
    -0.72
    __*/
    -0.69
    новништво
    -0.67
     AttributeSet
    -0.67
     مرئيه
    -0.66
    SequentialGroup
    -0.66
    providedIn
    -0.66
    mybatisplus
    -0.64
    POSITIVE LOGITS
     en
    0.90
    en
    0.71
    RU
    0.65
    EN
    0.63
    ru
    0.63
     fr
    0.60
     EN
    0.59
    En
    0.58
    fr
    0.57
     de
    0.56
    Activations Density 0.277%

    No Known Activations