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. 10-GEMMASCOPE-RES-16K
    6. 3461
    Prev
    Next
    INDEX
    Explanations

    mentions of specific viruses and their interactions with medical treatments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Harlequin
    -0.84
    ing
    -0.83
     Luxor
    -0.83
    thâu
    -0.80
    har
    -0.77
     RUSSELL
    -0.77
     Rivera
    -0.75
     Cardinals
    -0.75
    es
    -0.74
    charAt
    -0.73
    POSITIVE LOGITS
    PMailer
    0.84
     Krak
    0.83
     Relo
    0.81
     Keats
    0.79
     übere
    0.75
    Krak
    0.74
    frameCount
    0.73
    igneurs
    0.73
    creep
    0.71
    trainer
    0.71
    Activations Density 1.093%

    No Known Activations