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. 20-GEMMASCOPE-RES-16K
    6. 4325
    Prev
    Next
    INDEX
    Explanations

    references to equality and justice in legal contexts

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

    "Equal" followed by legal or ethical concepts

    np_acts-logits-general · gemini-2.0-flash

    equal protection

    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
     يتيمه
    -0.86
    Personensuche
    -0.83
    __);
    -0.78
    archiviato
    -0.74
    出版年
    -0.72
    ]--;
    -0.69
    Хьажоргаш
    -0.68
     للاسماء
    -0.67
    winston
    -0.66
    >*/
    -0.65
    POSITIVE LOGITS
     footing
    0.75
     Opportunity
    0.62
    Opportunity
    0.60
     tremp
    0.60
    altezza
    0.59
     opportunity
    0.58
    opportunity
    0.56
    VERIFY
    0.56
     nhau
    0.55
     importância
    0.53
    Activations Density 0.190%

    No Known Activations