© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 104913
    Prev
    Next
    INDEX
    Explanations

    occurrences of mathematical symbols and expressions

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
    Negative Logits
    rungsseite
    -0.68
    MethodManager
    -0.67
     estekak
    -0.63
     Smal
    -0.56
     purpoſe
    -0.53
     AssemblyCulture
    -0.53
    ientras
    -0.50
     MainAxisSize
    -0.50
     paille
    -0.49
    VIAF
    -0.49
    POSITIVE LOGITS
     }^{
    0.84
    ^{
    0.75
     ^{
    0.68
    }^{
    0.68
    /**
    0.67
    )^{
    0.61
    |^{
    0.60
    <sup>
    0.59
    }}^{
    0.59
     }^{[
    0.56
    Activations Density 0.005%

    No Known Activations