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. 11568
    Prev
    Next
    INDEX
    Explanations

    legal terms and references related to statutes and decrees

    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
     Wiktionnaire
    -0.50
    ']").
    -0.49
    ")]
    
    -0.46
     excursion
    -0.46
     ard
    -0.45
     pā
    -0.43
    Jur
    -0.42
    ")));
    
    -0.42
     Sado
    -0.42
     Trip
    -0.41
    POSITIVE LOGITS
     decrees
    0.94
     decreto
    0.94
     AssemblyCompany
    0.94
     decree
    0.92
    findpost
    0.90
     Decree
    0.89
     décret
    0.84
    AndEndTag
    0.83
    RectangleBorder
    0.80
     Decreto
    0.78
    Activations Density 0.399%

    No Known Activations