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-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 7461
    Prev
    Next
    INDEX
    Explanations

    structured data related to software packages and their metadata

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     unknownFields
    -0.72
    fjspx
    -0.60
    ?>">
    -0.55
     кӀош
    -0.52
    staticmethod
    -0.50
     distanciation
    -0.50
    InSection
    -0.50
     SwiftUI
    -0.49
    Anhalt
    -0.49
    ItemBackground
    -0.49
    POSITIVE LOGITS
     node
    0.82
     Node
    0.75
    node
    0.71
     npm
    0.70
     NODE
    0.67
     ES
    0.66
     NPM
    0.65
    npm
    0.61
    NODE
    0.61
    Node
    0.61
    Activations Density 0.739%

    No Known Activations