© 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-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 12340
    Prev
    Next
    INDEX
    Explanations

    symbols and formatting related to mathematical expressions and equations

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

    programming code elements, particularly syntax components in various programming languages and mathematical notation.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 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
    TagMode
    -0.93
    sidemargin
    -0.73
    UnsafeEnabled
    -0.73
    تقاوى
    -0.73
     ویکی‌پدی
    -0.72
    RenderAtEndOf
    -0.71
    SequentialGroup
    -0.69
    tagHelperRunner
    -0.69
     مرئيه
    -0.67
     Мексичка
    -0.66
    POSITIVE LOGITS
    닥
    0.44
     ‘
    0.44
     “
    0.43
     '
    0.41
    !
    0.41
     inf
    0.40
     co
    0.40
     formal
    0.40
     partial
    0.40
     hook
    0.39
    Activations Density 0.966%

    No Known Activations