© 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. 100989
    Prev
    Next
    INDEX
    Explanations

    symbols or punctuation marks often associated with legal or formal text

    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
    expandindo
    -0.80
     ujednoznacz
    -0.76
     autorytatywna
    -0.73
     mergeFrom
    -0.73
    كويكب
    -0.73
    
    -0.69
    uxxxx
    -0.69
    CppMethod
    -0.69
     imagui
    -0.68
    Panamoan
    -0.67
    POSITIVE LOGITS
    “
    0.28
     therefore
    0.28
     därför
    0.27
    Therefore
    0.27
    ­
    0.26
    Once
    0.25
    因此
    0.24
     once
    0.23
    ậy
    0.23
    sunter
    0.23
    Activations Density 0.004%

    No Known Activations