Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 12725
    Prev
    Next
    INDEX
    Explanations

    legal terminology and procedural phrases related to court motions and judgments

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

    Legal filings and court procedures

    np_acts-logits-general · gemini-2.0-flash

    legal judgment orders

    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
     GetEnumerator
    -0.75
    хьтан
    -0.62
    Extinguishing
    -0.55
    creativecommons
    -0.51
     veto
    -0.50
     xlink
    -0.50
    routeProvider
    -0.49
     getSelected
    -0.49
    createServer
    -0.47
     IOError
    -0.47
    POSITIVE LOGITS
    TypedDataSet
    0.59
    parties
    0.56
     '\\;'
    0.55
     courthouse
    0.54
    Filing
    0.54
     scheduling
    0.54
     procédure
    0.53
     liti
    0.53
     filings
    0.53
     Order
    0.53
    Activations Density 2.084%

    No Known Activations