Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 5266
    Prev
    Next
    INDEX
    Explanations

    terms related to agriculture and land management practices

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

    Agricultural or conservation contexts

    np_acts-logits-general · gemini-2.0-flash

    agricultural conservation program allotment

    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
    WebElementEntity
    -0.94
    PerformLayout
    -0.82
    SourceChecksum
    -0.80
    +#+#
    -0.80
    ThroughAttribute
    -0.78
    Naissance
    -0.74
    WebVitals
    -0.74
     AssemblyCulture
    -0.72
    PageRoute
    -0.69
     Italijanski
    -0.69
    POSITIVE LOGITS
    sified
    0.45
     program
    0.44
     dis
    0.43
     set
    0.42
    bieter
    0.42
     code
    0.41
     payment
    0.39
     paiement
    0.39
     ka
    0.38
    setCode
    0.38
    Activations Density 0.232%

    No Known Activations