© 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. 102415
    Prev
    Next
    INDEX
    Explanations

    various symbols, particularly underscores and slashes, indicating formatting or structure in textual data

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

    process performance cluster stress

    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
     hendes
    -0.27
     nemlig
    -0.26
     TAMBÉM
    -0.26
     derfor
    -0.25
    WebElementEntity
    -0.24
     rowspan
    -0.24
     därför
    -0.24
     Libertadores
    -0.24
    krát
    -0.23
     Italijani
    -0.23
    POSITIVE LOGITS
     autorytatywna
    0.79
    MigrationBuilder
    0.74
    
    0.72
     AssemblyTitle
    0.71
     للمعارف
    0.70
     EconPapers
    0.68
     ✭✭
    0.67
    ніципалі
    0.66
     protoimpl
    0.65
    <unused28>
    0.65
    Activations Density 0.007%

    No Known Activations