© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 4540
    Prev
    Next
    INDEX
    Explanations

    references to specific biological or health-related conditions, treatments, or classifications

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

    technical and scientific terminology related to genetics, molecular biology, and medical research.

    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
     ujednoznacz
    -0.46
     <>",
    -0.43
     Leader
    -0.42
     conce
    -0.41
    子和
    -0.39
     simplifié
    -0.38
     emp
    -0.37
    prediction
    -0.37
    和
    -0.36
     reve
    -0.36
    POSITIVE LOGITS
     MainAxisSize
    0.55
     سكانية
    0.54
     arşivlendi
    0.53
    ſelf
    0.46
     zijne
    0.46
     defaultstate
    0.45
     oprot
    0.45
     ainfi
    0.44
    BagLayout
    0.44
    følgelig
    0.44
    Activations Density 0.524%

    No Known Activations