© 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. 27904
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Not in Any Lists

    No Comments

    Negative Logits
    parsedMessage
    -0.93
     '\\;'
    -0.87
    دانشنامهٔ
    -0.81
    tvguidetime
    -0.80
    CloseOperation
    -0.80
    bootstrapcdn
    -0.78
    webElement
    -0.75
     propOrder
    -0.74
    enderror
    -0.74
    
    -0.72
    POSITIVE LOGITS
    webElementXpaths
    1.29
    pro
    0.29
     zanahoria
    0.28
     destacados
    0.27
     Justiz
    0.27
     Histórico
    0.26
    ℚ
    0.26
     DIRECT
    0.26
     αντί
    0.26
    Pro
    0.26
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.