© 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-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 104559
    Prev
    Next
    INDEX
    Explanations

    terms related to agriculture and food systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    chauffer
    -0.37
     Builder
    -0.36
    menea
    -0.35
    builder
    -0.35
    chargez
    -0.35
    kabel
    -0.34
    NullCheck
    -0.34
     builder
    -0.34
    UpInside
    -0.34
    pen
    -0.33
    POSITIVE LOGITS
    TagMode
    0.62
     agriculture
    0.61
    GEBURTSDATUM
    0.59
     Roskov
    0.57
     cherchés
    0.57
    AntiForgeryToken
    0.57
    ftagPool
    0.56
     agro
    0.56
    TypedDataSet
    0.55
     jspb
    0.54
    Activations Density 0.027%

    No Known Activations