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. 1793
    Prev
    Next
    INDEX
    Explanations

    actions and events related to combat or fighting

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

    Preceding a fighter's last name

    np_acts-logits-general · gemini-2.0-flash

    fighter names and actions

    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
    providedIn
    -0.54
    dymyr
    -0.51
     själva
    -0.50
    NotFoundError
    -0.49
    ostom
    -0.47
    omonas
    -0.47
     CGSize
    -0.46
    érature
    -0.45
     eventType
    -0.45
    xae
    -0.44
    POSITIVE LOGITS
    __*/
    0.62
    MigrationBuilder
    0.60
     चीज़ों
    0.60
     Alembic
    0.56
    oredCriteria
    0.56
    twimg
    0.54
     countered
    0.53
    发表于
    0.53
     мәкал
    0.52
    Datuak
    0.52
    Activations Density 0.089%

    No Known Activations