© 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. 538
    Prev
    Next
    INDEX
    Explanations

    complex themes related to beauty and atmosphere in various contexts

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

    Prepositions followed by "the"

    np_acts-logits-general · gemini-2.0-flash

    otherwise

    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
    ByPrimaryKey
    -0.59
    voorbeeld
    -0.51
    webElementXpaths
    -0.48
    клопе
    -0.47
    ainville
    -0.46
     betul
    -0.46
    Weblinks
    -0.45
    RTDA
    -0.44
     actualidad
    -0.44
     comprende
    -0.44
    POSITIVE LOGITS
     otherwise
    1.90
    otherwise
    1.77
    Otherwise
    1.53
     Otherwise
    1.48
     altrimenti
    1.45
     ellers
    1.44
     OTHERWISE
    1.38
     jinak
    1.20
     sonst
    1.14
     ohnehin
    1.12
    Activations Density 0.353%

    No Known Activations