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. 20-GEMMASCOPE-RES-16K
    6. 9328
    Prev
    Next
    INDEX
    Explanations

    elements related to agricultural practices and production

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Agricultural crops and cultivation

    np_acts-logits-general · gemini-2.0-flash

    agriculture and crops

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     FontWeight
    -0.54
     MemoryStream
    -0.48
     detergente
    -0.45
    MemoryStream
    -0.44
    şiv
    -0.44
     Nước
    -0.44
    bile
    -0.43
     مرئيه
    -0.43
     wahr
    -0.43
    InfoWindow
    -0.42
    POSITIVE LOGITS
     crops
    1.37
     harvest
    1.30
     crop
    1.28
     cultivation
    1.26
     harvests
    1.14
     harvested
    1.14
     plantations
    1.13
     yield
    1.11
     planted
    1.08
     production
    1.08
    Activations Density 0.262%

    No Known Activations