© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 4044
    Prev
    Next
    INDEX
    Explanations

    terms associated with healing and shear forces in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Metcalf
    -0.93
     McClure
    -0.91
     Caleb
    -0.90
    Caleb
    -0.88
    QMetaType
    -0.84
    DispatchToProps
    -0.83
    europa
    -0.82
    pelo
    -0.80
     ویکی‌پدی
    -0.80
    InteropServices
    -0.80
    POSITIVE LOGITS
     Cass
    0.66
    lific
    0.66
    wikia
    0.65
    日閲覧
    0.64
     Pond
    0.63
    sims
    0.63
     Tark
    0.62
     Cog
    0.62
    illets
    0.62
     HIF
    0.61
    Activations Density 0.261%

    No Known Activations