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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 51894
    Prev
    Next
    INDEX
    Explanations

    terms related to antioxidant activities and their effects on oxidative stress

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    penup
    -0.38
     comunión
    -0.37
    sunter
    -0.37
     Massen
    -0.35
    复制代码
    -0.35
    unico
    -0.35
    ‌ی
    -0.34
    MathML
    -0.34
    talt
    -0.34
    waltung
    -0.33
    POSITIVE LOGITS
     ſind
    0.60
    rrggbb
    0.59
     препратки
    0.53
     deſt
    0.53
    tershire
    0.52
     tiguan
    0.52
    IsContent
    0.50
     Diſ
    0.50
    aarrggbb
    0.50
     PyObject
    0.48
    Activations Density 0.145%

    No Known Activations