© 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. 11-GEMMASCOPE-RES-16K
    11. 7836
    Prev
    Next
    INDEX
    Explanations

    references to familial 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 @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    jsdelivr
    -0.52
    setVerticalGroup
    -0.51
     שוליים
    -0.46
    setDo
    -0.41
    $_['
    -0.41
     AssemblyProduct
    -0.40
     lateinit
    -0.40
    JvmStatic
    -0.38
    BeanUtils
    -0.37
    outSlope
    -0.36
    POSITIVE LOGITS
     himself
    1.08
    himself
    0.90
     manly
    0.81
     Himself
    0.80
     masculinity
    0.77
     mascul
    0.75
     manhood
    0.73
     boyhood
    0.71
     his
    0.70
     Handsome
    0.69
    Activations Density 1.846%

    No Known Activations