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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 1416
    Prev
    Next
    INDEX
    Explanations

    terms related to agricultural products, specifically corn and wheat

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

    Grains or agricultural products

    np_acts-logits-general · gemini-2.0-flash

    corn and wheat crops

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     majorité
    -0.58
     ruines
    -0.48
     compagn
    -0.47
    agoza
    -0.47
    ERVIEW
    -0.47
     gomma
    -0.47
    anlage
    -0.46
    nių
    -0.45
     sitten
    -0.45
     enfans
    -0.45
    POSITIVE LOGITS
    
    0.79
    脚注の使い方
    0.69
     farmer
    0.67
     farmers
    0.65
    farmer
    0.64
     farming
    0.61
     Landwir
    0.61
     мәкалә
    0.60
    تقاوى
    0.60
     kaarangay
    0.60
    Activations Density 0.229%

    No Known Activations