© 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-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 102384
    Prev
    Next
    INDEX
    Explanations

    the occurrences of the token "ru" in various cases

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

    ru language code and analytical solutions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     conmigo
    -0.50
     Bersama
    -0.46
     sostenibilidad
    -0.45
     Milán
    -0.45
    Билгалдахарш
    -0.45
     przewod
    -0.44
     Khusus
    -0.44
     helados
    -0.43
     Sosten
    -0.43
     contigo
    -0.43
    POSITIVE LOGITS
     ru
    2.42
    Ru
    1.37
     Ru
    1.37
     RU
    1.30
    ru
    1.28
    RU
    1.15
     ру
    1.02
     ruf
    0.90
    Ruj
    0.88
     ruffle
    0.88
    Activations Density 0.001%

    No Known Activations