Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 10167
    Prev
    Next
    INDEX
    Explanations

    references to the coronavirus and the COVID-19 pandemic

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

    viruses and outbreaks

    np_acts-logits-general · gemini-2.0-flash

    infectious diseases and pandemics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     SEDS
    -0.70
    __":
    
    -0.59
    ExtendWith
    -0.58
    ftagPool
    -0.58
    fromnode
    -0.58
    ariConfig
    -0.57
     beginnetje
    -0.57
    >(),
    -0.57
    ništ
    -0.56
    AnchorStyles
    -0.56
    POSITIVE LOGITS
     pandemic
    0.87
    
    0.73
     impact
    0.60
     era
    0.60
     salg
    0.58
    bedingt
    0.58
    beding
    0.58
     crisis
    0.57
     financière
    0.55
     sonno
    0.55
    Activations Density 0.150%

    No Known Activations