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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 16377
    Prev
    Next
    INDEX
    Explanations

    legal terminology and references to legal entities or proceedings

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

    legal professions/firms

    np_acts-logits-general · gemini-2.0-flash

    legal counsel and advisors

    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
    •Law

    No Comments

    Negative Logits
    zwald
    -0.68
     Вікі
    -0.59
    BagConstraints
    -0.54
    AutoScaleMode
    -0.52
    zogen
    -0.52
    nologue
    -0.52
     pengh
    -0.52
    £
    -0.52
    responseText
    -0.52
    󠁢
    -0.51
    POSITIVE LOGITS
    TintMode
    0.66
     transactional
    0.63
    RegressionTest
    0.63
     advising
    0.61
     advises
    0.58
    DebuggerNonUser
    0.57
    parsedMessage
    0.55
     practice
    0.55
     advise
    0.55
    Counsel
    0.54
    Activations Density 0.261%

    No Known Activations