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-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 10215
    Prev
    Next
    INDEX
    Explanations

    content related to infectious diseases, specifically eye infections

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

    Infection or disease spread

    np_acts-logits-general · gemini-2.0-flash

    disease and host transmission

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    énage
    -0.48
    ordeel
    -0.42
     récon
    -0.41
    Cyfeiriadau
    -0.41
    iramente
    -0.41
    unders
    -0.40
    teer
    -0.40
    toHaveBeenCalled
    -0.40
     peman
    -0.39
     lò
    -0.39
    POSITIVE LOGITS
     spread
    1.90
     infection
    1.78
     spreading
    1.78
     Spread
    1.74
     virus
    1.68
     contagion
    1.68
     spreads
    1.67
    spread
    1.67
    Spread
    1.65
     infect
    1.63
    Activations Density 0.466%

    No Known Activations