© 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 - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 7650
    Prev
    Next
    INDEX
    Explanations

    references to the word "Bal" and its variations

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

    starting with "Bal" or "Ball"

    np_acts-logits-general · gemini-2.0-flash

    words starting with Bal or Ball

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    PreferredItem
    -0.45
     consi
    -0.38
     zau
    -0.32
     chico
    -0.31
    CPtr
    -0.31
    ĝo
    -0.31
     Richt
    -0.31
    constructor
    -0.30
    TextAppearance
    -0.30
    格好
    -0.30
    POSITIVE LOGITS
    Bal
    0.60
     Bal
    0.59
     المعيارى
    0.57
     Balak
    0.57
     Bals
    0.56
     Balla
    0.55
     BALL
    0.53
     Бал
    0.52
    Ball
    0.52
    Balk
    0.52
    Activations Density 0.137%

    No Known Activations