© 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. 3-GEMMASCOPE-RES-16K
    11. 8815
    Prev
    Next
    INDEX
    Explanations

    references to the built-in features and capabilities of products or devices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    elemField
    -1.03
     Signalez
    -0.93
     مشين
    -0.87
     AssemblyCulture
    -0.75
    :✨
    -0.74
     wireType
    -0.72
    ViewImports
    -0.67
    twimg
    -0.65
     viewType
    -0.64
    ChildScrollView
    -0.64
    POSITIVE LOGITS
    内置
    0.75
     specialized
    0.73
     proprietary
    0.70
     встроен
    0.70
     speciali
    0.68
     dedicated
    0.67
    専用の
    0.66
    独自の
    0.65
     speciale
    0.65
    isticated
    0.64
    Activations Density 0.447%

    No Known Activations