© 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. 20-GEMMASCOPE-RES-16K
    11. 3560
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and symbols, particularly in the context of formal definitions and theorems

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

    LaTeX math mode delimiters and math symbols

    np_acts-logits-general · gemini-2.0-flash

    mathematical symbols and notation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
     Pal
    -0.60
    RenderAtEndOf
    -0.56
    Pal
    -0.52
    unknownFields
    -0.52
     pal
    -0.48
     bed
    -0.46
    jsxFileName
    -0.46
    ảm
    -0.45
     su
    -0.44
    RequiresApi
    -0.44
    POSITIVE LOGITS
     getItemId
    0.79
     Савезне
    0.75
    displaystyle
    0.72
    SPATH
    0.64
     оригіналу
    0.62
     муніципалі
    0.62
     HasFactory
    0.61
    InjectAttribute
    0.61
     myſelf
    0.60
    sedown
    0.59
    Activations Density 0.202%

    No Known Activations