© 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. 23542
    Prev
    Next
    INDEX
    Explanations

    terms related to oxidation and reduction processes

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

    oxidation and degradation

    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
    RegistryLite
    -0.52
    ArgsConstructor
    -0.49
     useParams
    -0.47
    DispatchToProps
    -0.46
    IntoConstraints
    -0.45
     Bep
    -0.45
     Inters
    -0.44
     ім
    -0.44
    yym
    -0.44
     viewWillAppear
    -0.44
    POSITIVE LOGITS
     oxidation
    1.02
     Oxidation
    0.97
     oxid
    0.96
    oxidation
    0.94
    Oxid
    0.91
     Oxid
    0.89
    oxid
    0.78
     oxidizing
    0.76
    Ox
    0.71
    氧化
    0.70
    Activations Density 0.017%

    No Known Activations