© 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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 112137
    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
     '{@
    -0.58
     collection
    -0.40
    queryInterface
    -0.40
    collection
    -0.40
     peuples
    -0.39
     COLLECTION
    -0.38
     Collection
    -0.37
    posób
    -0.37
     Photo
    -0.36
     HAND
    -0.36
    POSITIVE LOGITS
     esterni
    5.63
     externes
    1.53
     חיצוניים
    1.38
     esterno
    1.33
     externos
    1.26
     autorytatywna
    1.24
     lenker
    1.23
     خارجية
    1.22
     external
    1.16
     للمعارف
    1.16
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.