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. 13622
    Prev
    Next
    INDEX
    Explanations

    terms related to public health and epidemiology

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

    epidemiology or disease outbreaks

    np_acts-logits-general · gemini-2.0-flash

    epidemics, disease, and outbreaks

    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
     regenerate
    -0.49
     regenerated
    -0.46
     alimony
    -0.45
     refinance
    -0.44
     photosynthesis
    -0.44
     BANKS
    -0.43
     remar
    -0.43
     regener
    -0.43
    regener
    -0.42
    Banks
    -0.42
    POSITIVE LOGITS
     epidemio
    1.39
     epidemic
    1.30
     epidemiological
    1.28
     epidemiology
    1.28
     Epide
    1.27
     Epidemio
    1.24
    Epide
    1.23
     epidemics
    1.21
     health
    1.21
    epide
    1.21
    Activations Density 0.575%

    No Known Activations