© 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 - 65k
    9. 16-GEMMASCOPE-RES-65K
    11. 27238
    Prev
    Next
    INDEX
    Explanations

    instances of text that mark the beginning of a new section or statement

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

    income tax

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     незавершена
    -0.83
    djangoproject
    -0.82
     المعيارى
    -0.71
    -------------</
    -0.70
    ArrowToggle
    -0.69
    ыгана
    -0.68
     RoutedEventArgs
    -0.67
     TextAlign
    -0.65
     Савезне
    -0.62
    ChildScrollView
    -0.60
    POSITIVE LOGITS
    APORE
    0.43
    期刊论文
    0.42
    seamnă
    0.41
    httphttps
    0.41
     elevada
    0.40
     kesk
    0.39
     challenged
    0.39
     siitä
    0.38
     meisten
    0.38
     often
    0.38
    Activations Density 0.084%

    No Known Activations