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. 20-GEMMASCOPE-RES-16K
    6. 13805
    Prev
    Next
    INDEX
    Explanations

    references to storytelling and narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "story" or "stories"

    np_acts-logits-general · gemini-2.0-flash

    stories and tellers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •Literature
    references to storytelling and narratives

    No Comments

    Negative Logits
    yntaxException
    -0.62
    ArrowToggle
    -0.60
    はじめに
    -0.59
    TintMode
    -0.56
    pada
    -0.55
    UEZ
    -0.54
    preds
    -0.53
     Espec
    -0.52
    kespea
    -0.52
    minton
    -0.52
    POSITIVE LOGITS
     stories
    1.37
    Stories
    1.27
    tellers
    1.23
     Stories
    1.22
    stories
    1.17
     story
    1.15
     Story
    1.08
     STORY
    1.05
     tale
    1.03
     tales
    1.02
    Activations Density 0.066%

    No Known Activations