© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 104493
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
     myſelf
    -0.61
    ſelf
    -0.56
     himſelf
    -0.56
     pleaſure
    -0.55
     houſe
    -0.54
    いいのか
    -0.52
     ſta
    -0.52
     themſelves
    -0.51
     itſelf
    -0.51
     combustibles
    -0.50
    POSITIVE LOGITS
     in
    1.00
     در
    0.88
     In
    0.84
    อยู่ใน
    0.75
     في
    0.74
     isIn
    0.73
    ใน
    0.72
     at
    0.70
     للمعارف
    0.70
     forState
    0.67
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.