© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 52611
    Prev
    Next
    INDEX
    Explanations

    dietary patterns related to unhealthy food choices, specifically high fat and high sugar items

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

    processed, refined, and sugary foods

    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
     contextLoads
    -0.51
    OrBuilder
    -0.49
    cyklopedia
    -0.47
     thuận
    -0.47
    タクシー
    -0.46
     Metzger
    -0.44
     thể
    -0.44
     odby
    -0.44
    Dilution
    -0.43
     reversal
    -0.42
    POSITIVE LOGITS
    UnusedPrivate
    0.66
    ThroughAttribute
    0.54
     junk
    0.46
     InputDecoration
    0.42
     diet
    0.42
     basura
    0.42
     defaultstate
    0.40
     CWE
    0.39
    mobileqq
    0.39
     alimentaires
    0.39
    Activations Density 0.019%

    No Known Activations