© 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. 104914
    Prev
    Next
    INDEX
    Explanations

    specific types and descriptions of bread and their characteristics

    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
    UniformLocation
    -0.50
    reonine
    -0.50
    TRAILING
    -0.47
     vertrou
    -0.45
    ramento
    -0.44
     Stratton
    -0.44
    íqu
    -0.43
    شناسی
    -0.43
     vectorielle
    -0.42
    arschijnlijk
    -0.42
    POSITIVE LOGITS
     loaves
    0.90
     bread
    0.79
     bakery
    0.77
     loaf
    0.74
     breads
    0.74
     Bread
    0.69
    🍞
    0.66
    Bread
    0.65
     Loaf
    0.63
    bread
    0.63
    Activations Density 0.020%

    No Known Activations