© 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. 9109
    Prev
    Next
    INDEX
    Explanations

    terms related to expansion or growth in various contexts

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

    "expansion" (or a variant)

    np_acts-logits-general · gemini-2.0-flash

    expansion and growth

    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
     Stroud
    -0.51
    PMailer
    -0.50
    テイン
    -0.49
    ELEM
    -0.48
    InlineData
    -0.48
    ❦
    -0.47
     isSet
    -0.47
    ‌آم
    -0.46
     Dundas
    -0.45
    himu
    -0.45
    POSITIVE LOGITS
    ChildScrollView
    1.03
     horizons
    0.85
     expansions
    0.84
    EXPAND
    0.82
     Expansion
    0.81
    Expan
    0.79
     Expand
    0.79
     StatefulWidget
    0.77
     outwards
    0.76
     Expan
    0.76
    Activations Density 0.107%

    No Known Activations