© 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. 31-GEMMASCOPE-RES-131K
    11. 2372
    Prev
    Next
    INDEX
    Explanations

    phrases related to product selection and customer service

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

    our

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    IBarButtonItem
    -0.41
    自分は
    -0.41
    assertAll
    -0.39
    yaf
    -0.38
    ragamo
    -0.38
    subfigure
    -0.38
    tableFuture
    -0.37
     свое
    -0.36
    ніципалі
    -0.36
     ویکی‌پدیا
    -0.36
    POSITIVE LOGITS
     our
    2.19
     nossa
    1.58
    我们的
    1.58
     nosso
    1.57
    Our
    1.56
     nossos
    1.53
     nuestro
    1.52
    our
    1.49
    我們的
    1.48
     nuestra
    1.47
    Activations Density 0.150%

    No Known Activations