© 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. 10152
    Prev
    Next
    INDEX
    Explanations

    references to oats and oatmeal-related products

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

    oats, oatmeal, porridge

    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
     Landau
    -0.48
    sendRedirect
    -0.46
     Barrera
    -0.44
     Xiong
    -0.44
     vektör
    -0.44
     Krieger
    -0.42
    principalColumn
    -0.42
     Felici
    -0.42
     Chiu
    -0.42
     Gentry
    -0.42
    POSITIVE LOGITS
    Oat
    1.22
     oats
    1.18
     Oats
    1.15
     oatmeal
    1.14
     Oatmeal
    1.13
     oat
    0.99
     Oat
    0.98
     avena
    0.95
    oat
    0.82
     porridge
    0.80
    Activations Density 0.004%

    No Known Activations