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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 5071
    Prev
    Next
    INDEX
    Explanations

    elements related to programming and API calls

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     للمعارف
    -0.62
    migrationBuilder
    -0.58
     riuscito
    -0.58
     שוליים
    -0.57
     invokingState
    -0.56
    /");
    -0.53
    /")
    -0.52
    IVEREF
    -0.51
    Externé
    -0.51
     Réponses
    -0.50
    POSITIVE LOGITS
    &
    1.70
    \&
    1.27
    }&
    1.25
     '&
    1.18
    +"&
    1.17
     "&
    1.14
    '&
    1.07
    .&
    1.06
    )&
    1.05
    &&
    1.05
    Activations Density 0.289%

    No Known Activations