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. 21-GEMMASCOPE-RES-16K
    6. 454
    Prev
    Next
    INDEX
    Explanations

    references to agricultural practices and crop production

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    difice
    -0.51
    ArgumentParser
    -0.50
     noexcept
    -0.49
    UIControlState
    -0.48
     tenues
    -0.48
     dirancang
    -0.48
    viewDidLoad
    -0.47
     Architekt
    -0.45
     Comfort
    -0.45
    Život
    -0.45
    POSITIVE LOGITS
     harvest
    1.55
     harvested
    1.52
     harvesting
    1.39
     harvests
    1.29
     production
    1.25
    harvest
    1.23
     yield
    1.21
     Harvesting
    1.19
    Harvest
    1.16
     yields
    1.13
    Activations Density 0.266%

    No Known Activations