© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 9261
    Prev
    Next
    INDEX
    Explanations

    references to agricultural practices and crop management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MessageOf
    -0.84
     שוליים
    -0.72
     الحره
    -0.66
     تضيفلها
    -0.65
    RegressionTest
    -0.63
    AnchorStyles
    -0.61
    帖最后由
    -0.60
     kasarigan
    -0.60
     Prejudice
    -0.59
    mangle
    -0.58
    POSITIVE LOGITS
     cultivation
    0.80
     production
    0.78
     cropping
    0.65
    production
    0.64
     crops
    0.64
     growing
    0.64
     productions
    0.63
     monoc
    0.62
     rotation
    0.61
     culti
    0.60
    Activations Density 0.266%

    No Known Activations