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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 6525
    Prev
    Next
    INDEX
    Explanations

    information related to specific strains and lineages of viruses, particularly in the context of HIV

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    berday
    -0.60
     Idd
    -0.56
     Roskov
    -0.56
     quarantined
    -0.55
    Rüyada
    -0.53
    obium
    -0.51
     Coronavirus
    -0.51
    andere
    -0.51
     band
    -0.50
     FEATURE
    -0.49
    POSITIVE LOGITS
     Omicron
    1.17
     omicron
    1.04
     variants
    0.98
     Delta
    0.97
     variant
    0.95
     unvaccinated
    0.95
     variante
    0.93
     Variant
    0.91
     delta
    0.90
     Variants
    0.88
    Activations Density 0.117%

    No Known Activations