© 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. 27821
    Prev
    Next
    INDEX
    Explanations

    mentions of spare items or time

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

    spare parts, time, space, or to avoid

    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
    zzleHttp
    -0.62
    KommentareTeilen
    -0.55
    Slf
    -0.54
    lineTo
    -0.52
    glBegin
    -0.49
     AppComponent
    -0.49
     alignItems
    -0.47
     toiture
    -0.46
     Sitten
    -0.45
     Richt
    -0.45
    POSITIVE LOGITS
     spare
    2.20
    spare
    2.08
    Spare
    2.05
     Spare
    2.02
     spares
    1.55
     spared
    1.25
     repuesto
    1.20
     sparing
    1.13
     запас
    0.87
     rechange
    0.81
    Activations Density 0.001%

    No Known Activations