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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 7956
    Prev
    Next
    INDEX
    Explanations

    terms associated with oxidative stress and antioxidant mechanisms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     المعيارى
    -0.73
    таратура
    -0.73
    Jeografia
    -0.70
    }{|
    -0.68
    LayoutStyle
    -0.68
    Hauptartikel
    -0.66
    Personendaten
    -0.66
    ennon
    -0.64
    opel
    -0.64
    nEnter
    -0.63
    POSITIVE LOGITS
     oxidative
    1.07
     antioxidants
    1.01
     Oxid
    1.00
    Oxid
    0.99
     antioxidant
    0.98
    oxidants
    0.97
     antioxid
    0.96
     oxid
    0.96
     oxygen
    0.94
     Antioxidant
    0.94
    Activations Density 0.444%

    No Known Activations