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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 7155
    Prev
    Next
    INDEX
    Explanations

    elements related to zoonotic disease transmission dynamics between humans and animals

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

    Transmission or spread of disease/pathogens

    np_acts-logits-general · gemini-2.0-flash

    routes of 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
    GenerationType
    -0.50
    isfile
    -0.47
    (()
    -0.47
    ekš
    -0.46
    tigkeits
    -0.46
    __.__
    -0.46
     utilisons
    -0.46
    machus
    -0.45
     terk
    -0.45
     schie
    -0.44
    POSITIVE LOGITS
     transmission
    1.01
     exposures
    0.95
     exposure
    0.94
     Transmission
    0.92
    Transmission
    0.89
     infected
    0.89
     contaminated
    0.88
    transmission
    0.88
     Exposure
    0.82
     TRANSMISSION
    0.79
    Activations Density 1.125%

    No Known Activations