Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 9920
    Prev
    Next
    INDEX
    Explanations

    medical terminology related to diseases and their classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ArgsConstructor
    -0.49
    inko
    -0.46
     escaped
    -0.46
     pulumi
    -0.46
     Fairmont
    -0.45
     acrobat
    -0.45
    SBATCH
    -0.45
     escaping
    -0.44
    prepend
    -0.44
     bumper
    -0.43
    POSITIVE LOGITS
     Disease
    0.75
    Disease
    0.71
     disease
    0.69
     ziekte
    0.66
     DISEASE
    0.65
     maladie
    0.64
    disease
    0.63
     illness
    0.61
     Krankheit
    0.61
     diseased
    0.60
    Activations Density 0.430%

    No Known Activations