© 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. 16-GEMMASCOPE-RES-65K
    11. 31644
    Prev
    Next
    INDEX
    Explanations

    instances of the French word "qu" and variations of it

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    informal contractions like makin'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     dan
    -0.67
     
    -0.66
     regular
    -0.63
     #
    -0.60
     der
    -0.60
     om
    -0.59
    IGA
    -0.57
     a
    -0.57
     bar
    -0.56
     rich
    -0.55
    POSITIVE LOGITS
     متعلقه
    1.09
     مشين
    1.04
     שוליים
    1.02
     فريبيس
    0.84
    出版年
    0.81
     AssemblyProduct
    0.79
     وتسجيلات
    0.79
     nephe
    0.79
    Sucesor
    0.78
    writeFieldEnd
    0.78
    Activations Density 0.233%

    No Known Activations