© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 8047
    Prev
    Next
    INDEX
    Explanations

    legal terminology and references to regulations or statutes

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

    U.S.C. citations

    np_acts-logits-general · gemini-2.0-flash

    U.S.C. statutes and sections

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     face
    -0.57
     faces
    -0.52
    autoreleasepool
    -0.51
     presence
    -0.50
     presencia
    -0.49
     cappuccio
    -0.49
     présence
    -0.48
     Face
    -0.45
    Face
    -0.45
    棘
    -0.45
    POSITIVE LOGITS
     kasarigan
    0.87
    bootstrapcdn
    0.82
    QMetaType
    0.77
     كومونز
    0.77
    XmlAccessorType
    0.73
    expandindo
    0.72
     nahilalakip
    0.71
    >');
    0.68
    BeginContext
    0.67
    })));
    0.67
    Activations Density 0.899%

    No Known Activations