© 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. 10-GEMMASCOPE-RES-16K
    11. 8589
    Prev
    Next
    INDEX
    Explanations

    syntax elements and structure in code or programming-related content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    richTextPanel
    -0.61
    δας
    -0.59
     EClass
    -0.58
     >=",
    -0.58
    :✨
    -0.57
    vernight
    -0.56
    ècie
    -0.56
     authorship
    -0.55
    windowFixed
    -0.55
    parseFrom
    -0.54
    POSITIVE LOGITS
    WebVitals
    0.69
    bootstrapcdn
    0.68
     AssemblyTitle
    0.61
    kháu
    0.59
    MathML
    0.57
    //
    0.54
     JpaRepository
    0.52
    ComponentModel
    0.52
    ChildScrollView
    0.51
    تقاوى
    0.49
    Activations Density 0.530%

    No Known Activations