© 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. 31-GEMMASCOPE-RES-16K
    11. 9765
    Prev
    Next
    INDEX
    Explanations

    references to familial relationships and marriages

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

    possessive constructions involving female family members (daughters, sisters, wives).

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    父子
    -0.87
     męski
    -0.86
     muž
    -0.81
     męskie
    -0.77
    的他
    -0.77
    的男人
    -0.75
     lelaki
    -0.75
     pria
    -0.74
     himself
    -0.74
    彼は
    -0.73
    POSITIVE LOGITS
     girl
    1.26
     woman
    1.24
     female
    1.19
     women
    1.18
     lady
    1.14
     girls
    1.13
    woman
    1.10
     Girl
    1.06
     daughter
    1.05
    girl
    1.04
    Activations Density 0.813%

    No Known Activations