© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 18-GEMMASCOPE-RES-16K
    11. 15342
    Prev
    Next
    INDEX
    Explanations

    references to mathematical symbols and packages in LaTeX

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

    "math"

    np_acts-logits-general · gemini-2.0-flash

    math or Math start words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    parseFrom
    -0.73
     myſelf
    -0.72
    Geplaatst
    -0.70
     paroisse
    -0.69
     Jefus
    -0.69
    skosten
    -0.69
    setViewportView
    -0.68
     comigo
    -0.67
     Monfieur
    -0.66
     Efq
    -0.66
    POSITIVE LOGITS
     Mathis
    1.03
     MATH
    0.98
     Math
    0.95
     math
    0.90
    matical
    0.84
    math
    0.81
     Mathi
    0.81
    Math
    0.80
     Mathilde
    0.76
    MATH
    0.75
    Activations Density 0.076%

    No Known Activations