© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 18565
    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
     verrez
    -0.35
     contactez
    -0.33
     courrier
    -0.31
     quitar
    -0.31
    ToRemove
    -0.31
    æg
    -0.29
     ficando
    -0.29
    ตัด
    -0.28
    ərbaycan
    -0.28
     बह
    -0.28
    POSITIVE LOGITS
    dotenv
    5.44
     dotenv
    1.77
    bootstrapcdn
    0.84
    ValueStyle
    0.82
    chromedriver
    0.77
    DockStyle
    0.73
    medriver
    0.72
    Getenv
    0.69
    AddTagHelper
    0.69
    bcryptjs
    0.68
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.