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. 40-GEMMASCOPE-RES-16K
    6. 1832
    Prev
    Next
    INDEX
    Explanations

    references to viral infections and disease outbreaks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ConstraintMaker
    -0.48
     wireType
    -0.47
    mtliche
    -0.45
     makeStyles
    -0.39
    ߳
    -0.39
    olisme
    -0.38
    ymce
    -0.38
    >{@
    -0.38
     Milla
    -0.37
     otomatig
    -0.36
    POSITIVE LOGITS
     outbreak
    0.93
     surveillance
    0.93
     outbreaks
    0.90
     Outbreak
    0.80
     Surveillance
    0.79
     epiz
    0.73
     epidemio
    0.72
     epidemic
    0.69
     epidemiological
    0.68
     epidemiology
    0.66
    Activations Density 1.415%

    No Known Activations