Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 91342
    Prev
    Next
    INDEX
    Explanations

    terms related to antioxidant properties and activities

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

    antioxidant activities

    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
    StoryboardSegue
    -0.62
    RenderAtEndOf
    -0.55
    AutoresizingMask
    -0.51
    setViewName
    -0.49
    IsContent
    -0.48
     createState
    -0.47
    
    -0.45
    GraphicsUnit
    -0.45
    ⓧ
    -0.44
     Glue
    -0.44
    POSITIVE LOGITS
     antioxidant
    1.09
     antioxidants
    1.07
     Antioxidant
    0.93
    oxidants
    0.87
     antioxid
    0.82
    oxidant
    0.75
     oxidative
    0.52
    prefixer
    0.51
    veratrol
    0.49
     scavenging
    0.46
    Activations Density 0.009%

    No Known Activations