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. 4677
    Prev
    Next
    INDEX
    Explanations

    instances of punctuation and sentence structure

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

    Followed by a conjunction

    np_acts-logits-general · gemini-2.0-flash

    conjunctions and transitions

    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
    Not in Any Lists

    No Comments

    Negative Logits
     متعلقه
    -1.10
    tagHelperRunner
    -1.08
     فريبيس
    -1.04
     تضيفلها
    -1.03
    RenderAtEndOf
    -0.99
    UrlResolution
    -0.96
    \{\\
    -0.95
    featureID
    -0.95
    ✨:
    -0.93
    annica
    -0.93
    POSITIVE LOGITS
     But
    1.02
    But
    0.96
     but
    0.93
     so
    0.88
     So
    0.81
     what
    0.79
    So
    0.79
     What
    0.79
     Yet
    0.74
     then
    0.73
    Activations Density 0.228%

    No Known Activations