© 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 - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 880
    Prev
    Next
    INDEX
    Explanations

    terms related to legal actions and judicial processes

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

    Follows "was indicted," "was convicted," or "was arrested."

    np_acts-logits-general · gemini-2.0-flash

    arrested, indicted, convicted

    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
    RectangleBorder
    -0.74
    GEBURTSDATUM
    -0.67
    kháu
    -0.59
     beginnetje
    -0.59
     EconPapers
    -0.56
    }{*}{
    -0.52
     esternos
    -0.52
    ConstraintMaker
    -0.51
     &___
    -0.48
     når
    -0.48
    POSITIVE LOGITS
     separately
    0.67
     officiellement
    0.63
     privately
    0.61
    PreferredItem
    0.55
     locally
    0.55
     onData
    0.55
    enterOuterAlt
    0.54
    hoeddwyd
    0.54
     anonymously
    0.54
    hopped
    0.53
    Activations Density 0.666%

    No Known Activations