© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 1713
    Prev
    Next
    INDEX
    Explanations

    references to legal terms, legal entities, and the structure of legal proceedings

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

    followed by verbs like "is," "stated," or "'ll"

    np_acts-logits-general · gemini-2.0-flash

    legal entities and organizations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ujednoznacz
    -0.86
     @"/
    -0.71
    exitRule
    -0.71
    NameInMap
    -0.67
     nonUne
    -0.67
     estekak
    -0.66
     nakalista
    -0.61
     transfieras
    -0.61
    tagHelperRunner
    -0.58
     esetén
    -0.58
    POSITIVE LOGITS
    typeorm
    0.66
    erati
    0.56
     שלהם
    0.54
    reactstrap
    0.53
    zeitige
    0.52
    getMenuInflater
    0.51
    xase
    0.50
     للمعارف
    0.49
     itſelf
    0.49
    eake
    0.48
    Activations Density 2.774%

    No Known Activations