© 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-2-2B
    7. Residual Stream - 65k
    9. 13-GEMMASCOPE-RES-65K
    11. 25767
    Prev
    Next
    INDEX
    Explanations

    instances of the word "per" in various contexts indicating ratios or quantities

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    Portail
    -0.56
     ModelExpression
    -0.52
     utafitiHapana
    -0.51
    CodedInputStream
    -0.49
    #
    -0.49
     BoxDecoration
    -0.49
     estekak
    -0.48
    abestanden
    -0.47
    PreExecute
    -0.47
    startActivity
    -0.45
    POSITIVE LOGITS
     سكانية
    0.64
     each
    0.61
    EACH
    0.56
    ükemmel
    0.56
     chaque
    0.56
    יצוב
    0.55
     maîtres
    0.54
    éphane
    0.54
     bowiem
    0.53
    Chaque
    0.53
    Activations Density 0.093%

    No Known Activations