© 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-2-2B
    4. Residual Stream - 16k
    5. 19-GEMMASCOPE-RES-16K
    6. 685
    Prev
    Next
    INDEX
    Explanations

    references to templates in programming or technical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sizeCache
    -0.79
     bezig
    -0.58
    ostock
    -0.57
    !("{
    -0.56
     formality
    -0.56
    httphttps
    -0.56
    npr
    -0.53
    beza
    -0.53
    antMatchers
    -0.52
    umpul
    -0.52
    POSITIVE LOGITS
     templates
    0.95
     ModelExpression
    0.92
     Templates
    0.91
    templates
    0.83
     template
    0.82
    Patterns
    0.82
     patterns
    0.79
     模板
    0.78
     Patterns
    0.78
     TEMPLATE
    0.77
    Activations Density 0.104%

    No Known Activations