© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 263
    Prev
    Next
    INDEX
    Explanations

    legal terms and phrases related to court rulings and judgments

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

    phrases indicating the basis or reasoning behind court decisions

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

    for reasons or example

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     مشين
    -0.96
     resourceCulture
    -0.83
    XmlAccessType
    -0.78
    ThemeOverlay
    -0.74
    jspx
    -0.74
    Források
    -0.73
    ">//
    -0.73
    Джерела
    -0.72
    Mutagenicity
    -0.71
    Посилання
    -0.71
    POSITIVE LOGITS
     for
    1.32
     reasons
    1.00
    for
    0.99
     For
    0.96
    For
    0.94
     Reasons
    0.84
    Reasons
    0.78
     FOR
    0.77
    reasons
    0.73
     razones
    0.69
    Activations Density 0.224%

    No Known Activations