© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 6035
    Prev
    Next
    INDEX
    Explanations

    legal terminology and references to court cases

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

    Legal contexts concerning torts and breaches

    np_acts-logits-general · gemini-2.0-flash

    legal action breach contract

    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
     <<<<<<<<<<<<<<
    -0.75
     purpoſe
    -0.67
    ValueGeneration
    -0.66
     Hearings
    -0.60
     myſelf
    -0.58
     tslint
    -0.58
     Cune
    -0.58
    uesta
    -0.57
     становника
    -0.56
     ویکی‌پدیا
    -0.56
    POSITIVE LOGITS
    mybatisplus
    0.81
    AsUp
    0.62
     contract
    0.60
     common
    0.58
     contracts
    0.56
     breach
    0.54
     contractual
    0.54
     Contracts
    0.53
    CONTRACT
    0.53
    Contract
    0.52
    Activations Density 2.116%

    No Known Activations