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. 10968
    Prev
    Next
    INDEX
    Explanations

    specific coding or mathematical terms and phrases related to programming or data analysis

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

    Characters often followed by punctuation

    np_acts-logits-general · gemini-2.0-flash

    median PFS

    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
    +#+#
    -1.23
     للمعارف
    -1.16
    enumi
    -1.15
    Билгалдахарш
    -1.15
     تانيه
    -1.11
    OGND
    -1.10
     дописавши
    -1.08
     فريبيس
    -1.05
    expandindo
    -1.00
     שוליים
    -0.99
    POSITIVE LOGITS
     
    0.61
     (
    0.59
     [
    0.52
    ,
    0.52
    .
    0.51
     P
    0.51
     B
    0.51
    a
    0.50
     a
    0.48
    :
    0.47
    Activations Density 1.355%

    No Known Activations