© 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. 3889
    Prev
    Next
    INDEX
    Explanations

    comparative phrases involving demographics or characteristics of groups

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

    words and phrases that define or describe something (like "is a", "is", etc.).

    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
     redenen
    -0.37
     voorwaarden
    -0.34
     برانيه
    -0.34
     mijne
    -0.34
     zijne
    -0.33
     Taktlose
    -0.33
     tiada
    -0.32
    webElementXpaths
    -0.32
     verschillen
    -0.31
    zelfde
    -0.31
    POSITIVE LOGITS
    ViewImports
    0.58
    pote
    0.57
     consortium
    0.54
     XO
    0.53
    aldi
    0.53
    entre
    0.53
     mé
    0.52
     PSM
    0.52
    wieder
    0.52
    aix
    0.52
    Activations Density 0.726%

    No Known Activations