© 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. 9110
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to foundational elements and frameworks in various disciplines

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

    preceding "for" or "of."

    np_acts-logits-general · gemini-2.0-flash

    core element or basis

    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
    titleMargin
    -0.76
    UserScript
    -0.68
    PYX
    -0.68
    ConverterFactory
    -0.65
    ruptedException
    -0.62
     SafeMath
    -0.61
     useStyles
    -0.61
    setVerticalGroup
    -0.60
    FilterChain
    -0.60
    CompilerServices
    -0.60
    POSITIVE LOGITS
     for
    0.93
     bagi
    0.85
     utama
    0.76
    spunkt
    0.66
     point
    0.62
    之一
    0.62
     against
    0.59
     zugleich
    0.57
    verwijspagina
    0.55
     для
    0.54
    Activations Density 0.503%

    No Known Activations