© 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-2-9B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 5050
    Prev
    Next
    INDEX
    Explanations

    elements related to responses and questions in a structured format, possibly indicating a focus on interactions in a coding or troubleshooting context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 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
    PerformLayout
    -0.56
     surla
    -0.52
    oredCriteria
    -0.51
    SpringRunner
    -0.50
    曖昧さ回避
    -0.50
     Walkover
    -0.49
    TagMode
    -0.49
     الاطلاع
    -0.48
    ViewImports
    -0.48
     <>",
    -0.47
    POSITIVE LOGITS
     itself
    0.37
     externi
    0.36
    ⓧ
    0.36
    Jegyzetek
    0.34
    clearfix
    0.34
     rerum
    0.32
     pattern
    0.32
    MathML
    0.32
    Pattern
    0.31
     Secondary
    0.31
    Activations Density 14.076%

    No Known Activations