© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 5377
    Prev
    Next
    INDEX
    Explanations

    references to spouses and partners, particularly focusing on the term "wife."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    olol
    -0.49
    tamol
    -0.47
    specialchars
    -0.47
    eynman
    -0.47
    ooc
    -0.41
    بوابة
    -0.41
    flow
    -0.40
     deny
    -0.40
    Див
    -0.40
     Donat
    -0.40
    POSITIVE LOGITS
     wife
    1.20
     Wife
    1.14
     WIFE
    1.13
    Wife
    1.07
     husband
    1.07
     spouse
    1.03
     Husband
    0.97
     Spouse
    0.96
    Husband
    0.93
    Spouse
    0.92
    Activations Density 0.064%

    No Known Activations