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. 20-GEMMASCOPE-RES-131K
    6. 122870
    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
     totalCount
    -0.65
     WaitForSeconds
    -0.53
     BoxDecoration
    -0.53
    HomeAsUpEnabled
    -0.53
     maxHeight
    -0.51
    httphttps
    -0.51
     DbSet
    -0.50
     faſt
    -0.49
     NSCoder
    -0.49
    InSection
    -0.48
    POSITIVE LOGITS
    _
    1.27
    \_
    0.90
    ‐
    0.75
    -
    0.71
    _{
    0.70
    }_
    0.67
    -​
    0.65
    ‑
    0.62
    '_
    0.60
     _
    0.59
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.