© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 38-GEMMASCOPE-RES-16K
    11. 11514
    Prev
    Next
    INDEX
    Explanations

    mentions of family relationships and personal connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     istrinya
    -0.96
    娶
    -0.81
     vợ
    -0.68
     obrigado
    -0.64
    俺は
    -0.61
    僕は
    -0.61
     wives
    -0.60
     Obrigado
    -0.60
    妻子
    -0.57
     rád
    -0.57
    POSITIVE LOGITS
     husband
    2.22
    husband
    1.84
     Husband
    1.72
     husbands
    1.65
    Husband
    1.64
     marido
    1.47
     boyfriend
    1.46
     hubby
    1.44
     marito
    1.37
     esposo
    1.33
    Activations Density 0.379%

    No Known Activations