© 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-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 4824
    Prev
    Next
    INDEX
    Explanations

    references to family dynamics and relationships

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

    "Her" followed by "husband."

    np_acts-logits-general · gemini-2.0-flash

    wife's husband

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    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
    -1.23
     wives
    -1.02
     his
    -1.01
     seinen
    -0.94
     wife
    -0.92
    wife
    -0.92
    his
    -0.91
    妻子
    -0.87
     seine
    -0.85
     Wife
    -0.84
    POSITIVE LOGITS
     husband
    1.80
    husband
    1.40
     Husband
    1.25
     suaminya
    1.23
     marido
    1.23
     marito
    1.21
     husbands
    1.19
    Husband
    1.19
     esposo
    1.18
     boyfriend
    1.10
    Activations Density 0.291%

    No Known Activations