© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 101126
    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
    Negative Logits
    发表于
    -0.47
     troll
    -0.45
    iecie
    -0.44
    ➟
    -0.43
     albu
    -0.43
     scri
    -0.43
    dostęp
    -0.42
     באתר
    -0.42
    %@",
    -0.41
    SPJ
    -0.41
    POSITIVE LOGITS
     faſt
    0.63
     pouvoit
    0.60
     feroit
    0.59
    ſelf
    0.58
    ſelves
    0.56
     órg
    0.54
     wzgl
    0.53
     quæ
    0.52
    ✭✭
    0.52
     vė
    0.52
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.