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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 7-GEMMASCOPE-TRANSCODER-16K
    4. 7081
    Prev
    Next
    INDEX
    Explanations

    intense emotional dialogue with threats and protests

    oai_token-act-pair · gemini-2.0-flash

    !"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autorytatywna
    -0.71
    GEBURTSDATUM
    -0.69
     للمعارف
    -0.69
     насељу
    -0.69
    AsUp
    -0.67
     beginnetje
    -0.65
     الحره
    -0.62
     **/
    
    -0.61
    ilight
    -0.59
    rophore
    -0.59
    POSITIVE LOGITS
     onItemClick
    0.56
    انجليز
    0.44
     numé
    0.44
    AutoresizingMask
    0.43
     gegebenen
    0.43
    vábbi
    0.42
     distracted
    0.41
     Arxivat
    0.41
    ять
    0.40
     Germania
    0.40
    Activations Density 0.962%

    No Known Activations