© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 2056
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     الحره
    -0.69
    msgTypes
    -0.68
     ویکی‌پدیا
    -0.65
    期刊论文
    -0.61
    ymce
    -0.61
    yethylene
    -0.60
    /*
    -0.59
    تقاوى
    -0.59
     ModelExpression
    -0.58
     متعلقه
    -0.58
    POSITIVE LOGITS
     skin
    0.75
     pores
    0.69
     healthy
    0.68
     antioxidant
    0.66
     collagen
    0.64
     acne
    0.64
     skincare
    0.63
     healthier
    0.63
     inflammation
    0.62
     imbalances
    0.62
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.