© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 282
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and expressions, particularly those involving variables and parameters in equations

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

    monetary values and mathematical expressions

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

    mathematical symbol patterns

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    NUMX
    -0.88
     auffi
    -0.82
     myſelf
    -0.82
    ^(@)
    -0.81
     Pingback
    -0.80
     Theſe
    -0.80
     ſtand
    -0.79
     ſte
    -0.78
     Jefus
    -0.77
    KommentareTeilen
    -0.77
    POSITIVE LOGITS
     $
    1.00
    <i>
    0.72
    <em>
    0.69
    ($
    0.66
     $\
    0.63
     ($
    0.60
     gql
    0.56
    }{$\
    0.54
    زيون
    0.54
    {$
    0.52
    Activations Density 0.034%

    No Known Activations