© 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. 10263
    Prev
    Next
    INDEX
    Explanations

    references to significant health concepts and medical conditions

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

    key terms from medical, academic, and scientific research texts, including health concepts, research methods, and biological processes.

    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
     חיצוניים
    -0.48
    RenderAtEndOf
    -0.38
     Wicidata
    -0.37
     Spare
    -0.36
    Spare
    -0.36
     Deep
    -0.36
     Jefe
    -0.35
    丁
    -0.35
    idorm
    -0.35
     Mø
    -0.35
    POSITIVE LOGITS
     AssemblyCulture
    0.60
    parsedMessage
    0.57
     getItemId
    0.54
    AutoField
    0.52
    styleable
    0.52
    DMETHOD
    0.52
    SBATCH
    0.52
    IntoConstraints
    0.47
    Gweler
    0.47
     pinulongan
    0.46
    Activations Density 0.334%

    No Known Activations