© 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. 21-GEMMASCOPE-RES-16K
    11. 7944
    Prev
    Next
    INDEX
    Explanations

    phrases indicating capability or possibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RenderAtEndOf
    -0.74
     ویکی‌پدی
    -0.69
     "..\..\..\
    -0.67
    TagMode
    -0.64
    TextAppearance
    -0.64
    ThroughAttribute
    -0.64
     ModelExpression
    -0.60
    Попис
    -0.59
    новниш
    -0.58
     }{@
    -0.57
    POSITIVE LOGITS
     easily
    1.63
     fácilmente
    1.58
     facilmente
    1.48
    easily
    1.45
     facilement
    1.27
    ได้
    1.20
     Easily
    1.16
    Easily
    1.13
     anytime
    1.12
     anywhere
    1.06
    Activations Density 0.562%

    No Known Activations