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. 10-GEMMASCOPE-RES-16K
    6. 12607
    Prev
    Next
    INDEX
    Explanations

    mathematical proofs and logical assertions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Lake
    -0.52
    NavController
    -0.50
    ={{
    -0.49
    [['
    -0.49
     AND
    -0.49
     Lakes
    -0.48
     /
    -0.48
     blo
    -0.48
    AspNetCore
    -0.47
    nyttet
    -0.47
    POSITIVE LOGITS
    RenderAtEndOf
    0.93
     RSSSF
    0.80
     propOrder
    0.78
    ьаж
    0.77
     DialogInterface
    0.72
     unknownFields
    0.71
    FXMLLoader
    0.69
    SharedCtor
    0.67
     дописавши
    0.66
     AssemblyProduct
    0.65
    Activations Density 1.070%

    No Known Activations