© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 545
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to vaccination and immunization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    buntu
    -0.68
    VISIBLE
    -0.63
    =$?
    -0.62
     مشين
    -0.61
    quirrel
    -0.57
    prehen
    -0.57
    ANCY
    -0.56
    tesse
    -0.56
    natur
    -0.55
    ciples
    -0.54
    POSITIVE LOGITS
     vaccine
    1.97
     vaccines
    1.89
     vaccination
    1.86
     vaccinations
    1.79
     vaccin
    1.78
     Vaccine
    1.73
     Vaccines
    1.71
     vaccinated
    1.70
     Vaccination
    1.66
    Vaccine
    1.60
    Activations Density 0.175%

    No Known Activations