© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 713
    Prev
    Next
    INDEX
    Explanations

    terms related to various types of people and their roles in society

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

    people or groups associated with specific activities or professions (e.g., shoppers, gamers, diaper-ers, world traders).

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 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
     Mada
    -0.41
     pinulongan
    -0.41
    WebElementEntity
    -0.40
    defn
    -0.39
    ServletException
    -0.39
    artifactId
    -0.39
     sprend
    -0.38
     Gom
    -0.38
    BRAS
    -0.38
     Matri
    -0.38
    POSITIVE LOGITS
     travellers
    0.63
     traveller
    0.58
     theorists
    0.58
     shippers
    0.57
     travelers
    0.56
     Voters
    0.56
     gardeners
    0.54
     poète
    0.54
     traveler
    0.54
     planners
    0.54
    Activations Density 0.445%

    No Known Activations