Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 1533
    Prev
    Next
    INDEX
    Explanations

    sports-related actions and achievements

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

    preceding "in" or "to"

    np_acts-logits-general · gemini-2.0-flash

    Reach in space

    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
    Personensuche
    -0.80
    enumi
    -0.80
    ContentAsync
    -0.79
    ChildScrollView
    -0.79
    OGND
    -0.79
     مرئيه
    -0.77
     فريبيس
    -0.76
    GEBURTSDATUM
    -0.76
     للاسماء
    -0.74
     محفوظة
    -0.72
    POSITIVE LOGITS
     header
    0.57
     substitute
    0.52
     unmarked
    0.51
    Substitute
    0.50
     Substitute
    0.50
     headers
    0.47
    threading
    0.46
    WireFormatLite
    0.44
     space
    0.43
     unfortunately
    0.43
    Activations Density 0.053%

    No Known Activations