© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 1114
    Prev
    Next
    INDEX
    Explanations

    clinical terms and concepts related to infectious diseases and therapies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ,
    -0.52
     K
    -0.42
     link
    -0.42
    so
    -0.39
    UNG
    -0.38
     titre
    -0.37
    <eos>
    -0.37
    ونه
    -0.37
    K
    -0.37
     Et
    -0.36
    POSITIVE LOGITS
    rungsseite
    0.81
    ynb
    0.73
     defaultstate
    0.73
     unknownFields
    0.72
    WithIOException
    0.71
     smtplib
    0.71
    getWriter
    0.69
     trajets
    0.69
     Entreprises
    0.68
    참고
    0.66
    Activations Density 1.683%

    No Known Activations