© 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. 18-GEMMASCOPE-RES-16K
    11. 1777
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to fines and penalties in legal contexts

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

    Financial penalties and fines

    np_acts-logits-general · gemini-2.0-flash

    fines and penalties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     '\\;'
    -0.83
     autorytatywna
    -0.77
    tagHelperRunner
    -0.76
     actionMode
    -0.76
     समीक्षाएं
    -0.71
     nahilalakip
    -0.70
    contentLoaded
    -0.65
    AddHtmlAttribute
    -0.65
     voraus
    -0.64
    SequentialGroup
    -0.64
    POSITIVE LOGITS
     fines
    1.59
     fine
    1.44
     fined
    1.43
     penalty
    1.38
     penalties
    1.35
     Fines
    1.32
    Fine
    1.17
     Penalty
    1.15
     Fine
    1.15
    fine
    1.14
    Activations Density 0.138%

    No Known Activations