Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 64920
    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
     spéciaux
    -0.44
    undra
    -0.39
     AspNetCore
    -0.38
    付
    -0.38
    queles
    -0.38
    asthan
    -0.37
    makaian
    -0.35
    ComponentModel
    -0.35
    casting
    -0.35
     kicking
    -0.35
    POSITIVE LOGITS
     VIAF
    5.56
    VIAF
    5.50
     ISNI
    1.72
    Autoritní
    1.61
    Bibliograf
    1.55
    viaf
    1.51
     للاسماء
    1.34
    OGND
    1.26
     SUDOC
    1.01
     LCCN
    0.98
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.