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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 3513
    Prev
    Next
    INDEX
    Explanations

    references to marriages and familial relationships

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

    Marriage and relationships

    np_acts-logits-general · gemini-2.0-flash

    names of wives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     suaminya
    -1.01
     her
    -1.00
     herself
    -0.98
     husband
    -0.95
    husband
    -0.90
     Husband
    -0.89
     boyfriend
    -0.84
     she
    -0.83
    boyfriend
    -0.82
    丈夫
    -0.81
    POSITIVE LOGITS
     wives
    1.00
     women
    0.94
     istrinya
    0.91
     wife
    0.90
    wife
    0.85
    wives
    0.83
     ladies
    0.82
     Wife
    0.81
     Wives
    0.81
     woman
    0.80
    Activations Density 0.216%

    No Known Activations