© 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. 15081
    Prev
    Next
    INDEX
    Explanations

    phrases related to memorial services and death celebrations

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

    Sympathy or condolences in memorials

    np_acts-logits-general · gemini-2.0-flash

    words of sympathy

    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
    Personendaten
    -0.60
    transQ
    -0.59
    ----</
    -0.52
     regular
    -0.51
     pitted
    -0.50
     domanda
    -0.47
    Revenir
    -0.47
    AndroidJUnit
    -0.45
    はじめに
    -0.45
    格兰
    -0.45
    POSITIVE LOGITS
     condolence
    0.96
     obituary
    0.93
     condolences
    0.93
     Condol
    0.92
     guestbook
    0.80
     Obituary
    0.80
     OBITUARY
    0.76
     Online
    0.74
     mourners
    0.74
    Online
    0.73
    Activations Density 0.012%

    No Known Activations