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

    Neuronpedia

    Jacobian LensNEW
    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. 20-GEMMASCOPE-RES-131K
    11. 10856
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     становника
    -0.83
     ChromeDriver
    -0.78
    ⟬
    -0.77
    ✨:
    -0.69
    enderror
    -0.68
    UnusedPrivate
    -0.65
     للاسماء
    -0.65
     jsPsych
    -0.64
    UserScript
    -0.64
     Normdatei
    -0.63
    POSITIVE LOGITS
     comigo
    0.37
     incluido
    0.35
     cœurs
    0.35
     perfeita
    0.34
     juzgar
    0.34
     Müller
    0.33
     agradecer
    0.32
     deeper
    0.31
     dieux
    0.31
     inconvénients
    0.31
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.