© 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-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 7327
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, specifically parentheses and function-related constructs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Closing parenthesis in code

    np_acts-logits-general · gemini-2.0-flash

    function followed by curly braces

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tri
    -0.62
    表
    -0.59
     club
    -0.57
     Tri
    -0.54
     motor
    -0.54
     Le
    -0.53
    tri
    -0.53
     back
    -0.52
    トゥ
    -0.52
     the
    -0.51
    POSITIVE LOGITS
    setVerticalGroup
    1.05
    InjectAttribute
    0.97
    tagHelperRunner
    0.96
     typelib
    0.95
     kasarigan
    0.95
    twimg
    0.93
     للاسماء
    0.91
    ArrowToggle
    0.90
     BoxDecoration
    0.90
    WireFormatLite
    0.89
    Activations Density 0.076%

    No Known Activations