© 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. 2215
    Prev
    Next
    INDEX
    Explanations

    references to central themes or concepts associated with "heart" and "core" in various contexts

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

    Prepositions before "the" or nouns

    np_acts-logits-general · gemini-2.0-flash

    at the heart or center

    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
     विश्वसनीयता
    -0.76
     समीक्षक
    -0.73
     Paglinawan
    -0.72
     AssemblyTitle
    -0.65
     FetchType
    -0.65
    :✨
    -0.63
    SpringBootTest
    -0.62
    GIH
    -0.60
    elemField
    -0.59
    NameInMap
    -0.59
    POSITIVE LOGITS
     center
    1.84
     centre
    1.66
    center
    1.60
     core
    1.56
     heart
    1.54
    中心
    1.37
    centre
    1.37
     CENTER
    1.37
     centers
    1.34
    core
    1.33
    Activations Density 0.267%

    No Known Activations