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
    4. Residual Stream - 131k
    5. 24-GEMMASCOPE-RES-131K
    6. 1071
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bỏng
    -0.47
     heaps
    -0.46
     Sus
    -0.44
    iconCls
    -0.44
    Sus
    -0.43
     gypsy
    -0.43
     cis
    -0.43
     Mist
    -0.43
     Brem
    -0.43
    settling
    -0.42
    POSITIVE LOGITS
    AutoField
    6.31
     defaultstate
    0.79
    ImageField
    0.76
    CharField
    0.68
    ArgumentParser
    0.68
    ChildScrollView
    0.67
     فريبيس
    0.66
    CodeAttribute
    0.64
    ValueGenerated
    0.62
     automatiques
    0.61
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.