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. 13296
    Prev
    Next
    INDEX
    Explanations

    phrases and patterns related to regular expressions and their operations

    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
    coroutines
    -0.64
     Untitled
    -0.63
     متعلقه
    -0.63
    مصادر
    -0.61
    Datuak
    -0.61
    endpush
    -0.61
    DispatchToProps
    -0.59
     neceff
    -0.58
    yaszt
    -0.58
    ::_('
    -0.58
    POSITIVE LOGITS
    regex
    0.96
     Regex
    0.92
     regex
    0.89
    Regex
    0.79
     RegExp
    0.77
     BeautifulSoup
    0.73
    regexp
    0.70
    RegExp
    0.70
     regexp
    0.69
    ParseException
    0.68
    Activations Density 0.620%

    No Known Activations