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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 7585
    Prev
    Next
    INDEX
    Explanations

    terms related to plant genetics and breeding

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

    scientific and technical terminology related to experimental methods, measurements, and statistical analysis in academic research.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Taktlose
    -0.47
     HasFactory
    -0.47
    帖最后由
    -0.43
    WebElementEntity
    -0.42
     polyps
    -0.41
    /*
    -0.40
     amnio
    -0.40
    EndInit
    -0.39
    fjspx
    -0.38
     bubbles
    -0.36
    POSITIVE LOGITS
     agronom
    0.55
     itinéraires
    0.50
    Trials
    0.47
     yield
    0.47
     manejo
    0.46
     Trials
    0.46
    Management
    0.46
     Yield
    0.45
    Yield
    0.45
     Crop
    0.45
    Activations Density 0.687%

    No Known Activations