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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 5449
    Prev
    Next
    INDEX
    Explanations

    medical terminology related to congenital conditions and genetic mutations

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

    technical medical terminology and details, particularly related to genetic conditions, medical case studies, and clinical descriptions.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    medical and genetic terminology in clinical case reports and scientific literature.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     wireType
    -0.63
     uLocal
    -0.51
    Promotion
    -0.50
    はじめに
    -0.50
     Promotion
    -0.48
    COUVER
    -0.46
     promotion
    -0.45
    promotion
    -0.45
    HtmlAttribute
    -0.44
    ➌
    -0.42
    POSITIVE LOGITS
     autos
    0.71
     defects
    0.67
     gene
    0.66
     inherited
    0.66
     defect
    0.65
     hereditary
    0.64
     mutation
    0.63
     Autos
    0.62
     mutations
    0.61
     defective
    0.61
    Activations Density 1.304%

    No Known Activations