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. 10912
    Prev
    Next
    INDEX
    Explanations

    text related to legal or formal contexts

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

    Starts a sentence after punctuation

    np_acts-logits-general · gemini-2.0-flash

    tokens starting brackets

    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
     itſelf
    -1.03
     myſelf
    -0.95
    ſelves
    -0.95
     purpoſe
    -0.87
     -->>
    -0.85
     Wikimedijinoj
    -0.84
    ſelf
    -0.84
     Anſ
    -0.83
     iſt
    -0.82
     pleaſure
    -0.82
    POSITIVE LOGITS
     oscuros
    0.58
     [
    0.57
    Then
    0.54
    [
    0.54
     ибо
    0.52
    したが
    0.52
    Chapter
    0.50
     затем
    0.50
     passagem
    0.49
     thence
    0.49
    Activations Density 0.680%

    No Known Activations