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. 11-GEMMASCOPE-RES-16K
    6. 5437
    Prev
    Next
    INDEX
    Explanations

    references to various types of buses and transit vehicles

    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
     eingeb
    -0.82
    ︎
    -0.80
    ghen
    -0.79
     flamingo
    -0.78
    mord
    -0.75
    σιμοποι
    -0.75
     Rena
    -0.73
     Tana
    -0.73
    ādā
    -0.72
    ghans
    -0.71
    POSITIVE LOGITS
     buses
    1.71
     bus
    1.70
     Bus
    1.66
     Buses
    1.53
     BUS
    1.52
     Busse
    1.51
    bus
    1.50
    Bus
    1.50
    BUS
    1.32
    buses
    1.31
    Activations Density 0.091%

    No Known Activations