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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 5443
    Prev
    Next
    INDEX
    Explanations

    references to links or connections within text

    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
     Majefty
    -1.03
    cabulary
    -0.82
     Hoh
    -0.80
    dafx
    -0.79
    eradish
    -0.78
     theſe
    -0.78
     ſeveral
    -0.78
     Monfieur
    -0.78
    typescript
    -0.77
     dépens
    -0.77
    POSITIVE LOGITS
     link
    1.85
     Link
    1.83
     LINK
    1.77
     links
    1.73
    Link
    1.66
    link
    1.62
    LINK
    1.57
     Links
    1.57
    links
    1.57
    Links
    1.48
    Activations Density 0.044%

    No Known Activations