© 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 - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 39740
    Prev
    Next
    INDEX
    Explanations

    code-related terms and structures, particularly those related to parameters and updates in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uxxxx
    -0.65
     gainera
    -0.61
    HasForeignKey
    -0.60
    thâu
    -0.57
     lisse
    -0.57
    criminator
    -0.57
    Rhestr
    -0.56
    ériale
    -0.56
    UnsafeEnabled
    -0.56
    ViewImports
    -0.55
    POSITIVE LOGITS
    ContentAsync
    0.56
    fromCharCode
    0.49
    setViewportView
    0.49
    Einzelnachweise
    0.48
    (:,:,
    0.46
    WebElementEntity
    0.44
    \|_{\
    0.44
    )$_
    0.44
     পরি
    0.43
    PerformLayout
    0.42
    Activations Density 0.201%

    No Known Activations