© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 59245
    Prev
    Next
    INDEX
    Explanations

    mentions of sheep and related terms

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

    sheep, ewes, lambs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    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
    verwijspagina
    -0.53
    alter
    -0.50
    Diaz
    -0.44
     Diaz
    -0.42
     via
    -0.41
     Paglinawan
    -0.39
     Holman
    -0.39
    Gina
    -0.39
    presence
    -0.38
    Legături
    -0.38
    POSITIVE LOGITS
     Sheep
    1.46
    Sheep
    1.40
     sheep
    1.34
    sheep
    1.14
     ewes
    0.93
    🐑
    0.88
     kambing
    0.86
     mutton
    0.83
     lambs
    0.82
     Livestock
    0.78
    Activations Density 0.005%

    No Known Activations