© 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. 6201
    Prev
    Next
    INDEX
    Explanations

    numerical data and statistical results related to medical or health metrics

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

    statistical measurements and medical data metrics.

    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
     Италијани
    -0.77
     Numerade
    -0.74
    EndGlobalSection
    -0.73
    nambuco
    -0.72
     jsPsych
    -0.66
     deſſen
    -0.63
    enumii
    -0.63
     geweſen
    -0.62
    <pad>
    -0.61
    ->___
    -0.61
    POSITIVE LOGITS
    UrlResolution
    0.38
     Hälfte
    0.37
     average
    0.35
     כן
    0.32
     mitad
    0.32
     enough
    0.31
    Démographie
    0.31
     juges
    0.30
     ENOUGH
    0.30
     fometimes
    0.29
    Activations Density 0.359%

    No Known Activations