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. 3201
    Prev
    Next
    INDEX
    Explanations

    dynamic and interactive descriptions related to shared experiences or narratives

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

    that start questions

    np_acts-logits-general · gemini-2.0-flash

    how, what, why

    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
    tocin
    -0.54
    thalam
    -0.50
    LookAnd
    -0.49
     تعدى
    -0.49
     Reuter
    -0.48
    ✎
    -0.48
     thoại
    -0.47
    ophenol
    -0.46
    ейс
    -0.46
    ktı
    -0.45
    POSITIVE LOGITS
     how
    2.15
    how
    1.59
     what
    1.54
     cómo
    1.47
     why
    1.41
    what
    1.27
     bagaimana
    1.25
    How
    1.24
     How
    1.20
    why
    1.16
    Activations Density 0.386%

    No Known Activations