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. 19-GEMMASCOPE-RES-16K
    6. 3619
    Prev
    Next
    INDEX
    Explanations

    occurrences of the prefix "vi-" and related terms, often associated with viral concepts or viral infections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    addPreferredGap
    -0.66
     dịch
    -0.56
     Mexique
    -0.56
     series
    -0.55
    liev
    -0.52
     Kugel
    -0.51
    classnames
    -0.51
    gehen
    -0.51
    olar
    -0.50
    ppon
    -0.50
    POSITIVE LOGITS
     Wib
    0.68
    GraphicsUnit
    0.65
     Wis
    0.62
     engraçadas
    0.61
     Vict
    0.61
     Viator
    0.60
    aksana
    0.57
     Viss
    0.56
     Vis
    0.56
     فريبيس
    0.55
    Activations Density 0.107%

    No Known Activations