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. 4197
    Prev
    Next
    INDEX
    Explanations

    terms related to religious institutions and their structures

    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
     sickle
    -0.59
     empires
    -0.56
     Reisedaten
    -0.56
     kingdoms
    -0.54
    Filmografie
    -0.53
    contentLoaded
    -0.53
     الحره
    -0.52
     parentage
    -0.52
     دیکھیے
    -0.52
     verru
    -0.52
    POSITIVE LOGITS
    出版年
    0.79
     monastic
    0.75
     monk
    0.69
    monk
    0.68
     monks
    0.67
     nun
    0.64
     convento
    0.64
     Monk
    0.63
     Monks
    0.62
     nuns
    0.62
    Activations Density 0.239%

    No Known Activations