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. 6618
    Prev
    Next
    INDEX
    Explanations

    syntax and punctuation patterns within numerical and mathematical contexts

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

    References, citations, or dates abbreviated by numbers

    np_acts-logits-general · gemini-2.0-flash

    days of the week

    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
     CreateTagHelper
    -0.88
     sobot
    -0.66
     متعلقه
    -0.65
     lenker
    -0.65
     numerus
    -0.65
    KommentareTeilen
    -0.65
     ElementRef
    -0.63
    DeleteBehavior
    -0.63
     InputDecoration
    -0.62
    prepareStatement
    -0.62
    POSITIVE LOGITS
     Tuesday
    0.77
    Tuesday
    0.74
    2
    0.72
     martes
    0.60
     Dienstag
    0.58
     TUESDAY
    0.58
     Tuesdays
    0.55
     Wednesday
    0.54
     tuesday
    0.54
    XXII
    0.53
    Activations Density 0.678%

    No Known Activations