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. 5-GEMMASCOPE-RES-16K
    6. 14576
    Prev
    Next
    INDEX
    Explanations

    terms related to civil matters or civil law

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Tunisia
    -1.04
    LEncoder
    -0.99
     acorns
    -0.99
    memoized
    -0.93
     Tunisia
    -0.92
     Moscou
    -0.89
     anhänger
    -0.88
     artistique
    -0.87
     magique
    -0.87
     Paus
    -0.86
    POSITIVE LOGITS
     civil
    2.62
     Civil
    2.54
    Civil
    2.34
    civil
    2.20
     CIVIL
    2.14
     Civ
    1.53
     civile
    1.50
    CIV
    1.49
    Civ
    1.45
     civils
    1.38
    Activations Density 0.052%

    No Known Activations