© 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. 308
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal and procedural language

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

    important phrases and references in legal or formal discussions

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

    previous or earlier

    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
    ärs
    -0.58
    وفاته
    -0.55
     Signalez
    -0.54
     ISNI
    -0.53
     pinulongan
    -0.52
    forName
    -0.51
    ualitas
    -0.51
    WireFormatLite
    -0.51
    ISupport
    -0.50
    TagMode
    -0.49
    POSITIVE LOGITS
     previous
    3.55
     earlier
    3.16
    previous
    3.15
     previously
    3.13
     Previous
    2.93
    Previous
    2.91
     Previously
    2.85
     PREVIOUS
    2.82
    Previously
    2.81
    earlier
    2.79
    Activations Density 1.433%

    No Known Activations