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

    Neuronpedia

    Jacobian LensNEW
    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. 20-GEMMASCOPE-RES-16K
    11. 8864
    Prev
    Next
    INDEX
    Explanations

    specific medical terms and their associated conditions

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

    ending in "ly", "od", "phy", "ox", "ron", or "cyclo"

    np_acts-logits-general · gemini-2.0-flash

    polyg, hypo, nod

    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
    indd
    -0.48
     jButton
    -0.43
     fine
    -0.40
    conazole
    -0.40
    idue
    -0.39
    AMENT
    -0.38
     oper
    -0.38
     each
    -0.37
    '],'
    -0.36
    oling
    -0.35
    POSITIVE LOGITS
    IntoConstraints
    0.72
    abestanden
    0.71
     GenerationType
    0.70
     EconPapers
    0.70
     <>",
    0.70
     invokingState
    0.69
    Personensuche
    0.67
     للتو
    0.67
    memoized
    0.65
    InvalidProtocol
    0.64
    Activations Density 0.456%

    No Known Activations