© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 979
    Prev
    Next
    INDEX
    Explanations

    technical terms and specific details in scientific discourse related to viruses and drugs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/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.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     المعيارى
    -0.94
    AddTagHelper
    -0.77
    RenderAtEndOf
    -0.75
    MLLoader
    -0.73
    pshots
    -0.68
     pageContext
    -0.65
     AssemblyCulture
    -0.64
     Pote
    -0.63
    esgue
    -0.60
    वरण
    -0.60
    POSITIVE LOGITS
    系
    0.56
     member
    0.53
    系の
    0.53
    wiek
    0.50
    類
    0.49
    anyar
    0.48
    系的
    0.47
    CELLANEOUS
    0.47
    类的
    0.46
    elux
    0.46
    Activations Density 1.485%

    No Known Activations