© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 11251
    Prev
    Next
    INDEX
    Explanations

    references to community engagement and growth in research or public interest

    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
    UIImage
    -0.56
    llä
    -0.50
    initialValue
    -0.50
     UIImage
    -0.48
    engl
    -0.47
    Guer
    -0.47
     LIC
    -0.46
    ura
    -0.45
    Silly
    -0.45
    github
    -0.45
    POSITIVE LOGITS
     increasingly
    1.20
     growing
    1.04
    increasing
    1.02
    越来越
    1.00
     Increasing
    0.99
    growing
    0.98
    Increasing
    0.97
     increasing
    0.93
    越來越
    0.91
     Growing
    0.87
    Activations Density 0.197%

    No Known Activations