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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 104900
    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
     חיצוניים
    -0.54
    Chham
    -0.54
    utilisons
    -0.53
    delwed
    -0.52
    DeleteBehavior
    -0.50
    devServer
    -0.48
    GEBUR
    -0.46
    )];
    
    -0.44
     toiminta
    -0.44
     TÉCNICA
    -0.44
    POSITIVE LOGITS
    EIF
    2.25
     EIF
    2.17
    portál
    1.55
    jsii
    1.20
    setCharacter
    1.15
    mps
    1.08
    eef
    0.82
    MPS
    0.69
     MPS
    0.69
     eif
    0.57
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.