© 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-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 5443
    Prev
    Next
    INDEX
    Explanations

    references related to family relationships and genealogical connections

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

    family members who have died, particularly focusing on mentions of death within family narratives.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    references to family relationships and life events—especially deaths, widowhood, and spousal roles—in biographical or genealogical contexts.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    references to deceased spouses in biographical or genealogical texts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 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
     abi
    -0.41
     Perseus
    -0.35
    énario
    -0.33
     nhàng
    -0.33
    úblico
    -0.32
     (...
    -0.32
     Solana
    -0.32
     stupe
    -0.31
     sector
    -0.30
     rộng
    -0.30
    POSITIVE LOGITS
    RegressionTest
    0.57
     resourceCulture
    0.57
     asesinado
    0.52
    Билгалдахарш
    0.51
     виправивши
    0.50
    发表于
    0.50
    Cyfeiriadau
    0.50
     décédé
    0.49
    ValueStyle
    0.48
    SharedDtor
    0.48
    Activations Density 0.010%

    No Known Activations