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. 16-GEMMASCOPE-RES-16K
    6. 6384
    Prev
    Next
    INDEX
    Explanations

    content related to specialized fields, including healthcare, technology, and media

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

    that describe something

    np_acts-logits-general · gemini-2.0-flash

    technical entities and descriptions

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    Not in Any Lists

    No Comments

    Negative Logits
     gyhoeddwyd
    -0.68
    PreferredItem
    -0.64
    AndEndTag
    -0.63
    migrationBuilder
    -0.62
    ьаж
    -0.61
     élas
    -0.58
    tvguidetime
    -0.58
     étrangères
    -0.57
     culturelles
    -0.57
    URLEncoder
    -0.56
    POSITIVE LOGITS
     >=",
    0.70
     called
    0.69
     which
    0.68
     whose
    0.62
    RectangleBorder
    0.61
    which
    0.61
     ErrIntOverflow
    0.57
    whose
    0.57
     whoſe
    0.56
    참고
    0.55
    Activations Density 1.010%

    No Known Activations