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. 14153
    Prev
    Next
    INDEX
    Explanations

    terms related to book or media covers

    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
     Dumont
    -0.84
     Bianchi
    -0.66
     Fisch
    -0.66
    Nih
    -0.62
    ابد
    -0.61
    .~(\
    -0.61
    Wishlist
    -0.61
     Peters
    -0.60
     الاطلاع
    -0.58
    iasaan
    -0.58
    POSITIVE LOGITS
     Covers
    2.25
     cover
    2.25
     Cover
    2.23
     covers
    2.22
     COVER
    2.14
    cover
    2.12
    Cover
    2.12
    Covers
    2.10
    COVER
    1.94
    covers
    1.82
    Activations Density 0.046%

    No Known Activations