© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 8639
    Prev
    Next
    INDEX
    Explanations

    LaTeX package commands in the context of document preparation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ligiloj
    -0.62
     pleaſure
    -0.62
    AndEndTag
    -0.56
    coln
    -0.55
     Anſ
    -0.54
     متحده
    -0.54
     itſelf
    -0.54
     poffible
    -0.54
    delwed
    -0.54
     Jefus
    -0.52
    POSITIVE LOGITS
    usepackage
    2.59
    DllImport
    0.62
    documentclass
    0.57
     AssemblyTitle
    0.49
    endcsname
    0.45
    import
    0.45
     للاسماء
    0.44
    keyboardType
    0.42
    package
    0.40
    ️
    0.40
    Activations Density 0.009%

    No Known Activations