© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 3386
    Prev
    Next
    INDEX
    Explanations

    terminology related to dynamic systems and their characteristics

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

    "dynamic"

    np_acts-logits-general · gemini-2.0-flash

    dynamic analysis and modeling

    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
    ről
    -0.59
    kologi
    -0.58
     noires
    -0.56
    XtraReports
    -0.55
     eletrônico
    -0.55
     McCulloch
    -0.54
    ︎
    -0.54
     useAuth
    -0.54
     ControllerBase
    -0.53
     prácti
    -0.51
    POSITIVE LOGITS
     dyna
    0.91
     Dyn
    0.83
     dynamis
    0.80
    Dyn
    0.76
     EconPapers
    0.75
     dynamically
    0.74
    dyn
    0.74
    الإنجليزية
    0.72
     dynamic
    0.72
    dynamic
    0.71
    Activations Density 0.095%

    No Known Activations