© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 1674
    Prev
    Next
    INDEX
    Explanations

    references to authors and their collaborations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Gim
    -0.74
     Mier
    -0.72
     PMP
    -0.71
     Jefus
    -0.70
     Startseite
    -0.69
     cem
    -0.69
     Monfieur
    -0.68
     Gie
    -0.67
     Nasi
    -0.67
    inqu
    -0.67
    POSITIVE LOGITS
     authors
    1.56
    authors
    1.45
    Authors
    1.45
     Authors
    1.43
    author
    1.32
     author
    1.31
     Author
    1.29
     AUTHOR
    1.21
     AUTHORS
    1.16
    Author
    1.12
    Activations Density 0.066%

    No Known Activations