Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 3118
    Prev
    Next
    INDEX
    Explanations

    references to traditional marital roles and responsibilities

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

    Marriage, divorce, and husbands

    np_acts-logits-general · gemini-2.0-flash

    marriage and divorce

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aph
    -0.44
     
    -0.43
    ђе
    -0.41
     Miss
    -0.41
     the
    -0.40
     e
    -0.39
    miss
    -0.39
    뻗
    -0.39
      
    -0.38
     Tief
    -0.38
    POSITIVE LOGITS
     husbands
    1.08
     marital
    1.06
     husband
    1.05
     divorce
    1.02
     Husband
    1.00
    Husband
    0.96
     wives
    0.95
     Marital
    0.94
     matrimonial
    0.94
     spouses
    0.91
    Activations Density 0.216%

    No Known Activations