Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 56449
    Prev
    Next
    INDEX
    Explanations

    occurrences of mathematical expressions and formatting elements in LaTeX

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

    mathematical formulas in text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    CodeAttribute
    -0.49
    ImageContext
    -0.47
    furt
    -0.47
    >−
    -0.44
    niſſe
    -0.44
    ReusableCell
    -0.43
     prakty
    -0.43
    хіво
    -0.43
    principalColumn
    -0.42
     erreich
    -0.42
    POSITIVE LOGITS
    IntoConstraints
    0.57
     mathematical
    0.52
     math
    0.51
     plotly
    0.45
     mathematics
    0.44
     maths
    0.42
    mathematical
    0.42
    latex
    0.40
     sympy
    0.40
     mathematicians
    0.40
    Activations Density 0.052%

    No Known Activations