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-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 1031
    Prev
    Next
    INDEX
    Explanations

    references to Italian culture and cuisine

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

    Italy or Italian culture

    np_acts-logits-general · gemini-2.0-flash

    Italian food, people, and places

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Monfieur
    -0.71
    bibfield
    -0.53
     Chriftian
    -0.51
     barbati
    -0.51
     otomatig
    -0.50
     baterie
    -0.50
     fotografico
    -0.49
     isolato
    -0.48
     giornal
    -0.48
    
    -0.48
    POSITIVE LOGITS
     Italian
    0.77
     Italy
    0.74
    Italy
    0.71
    Italian
    0.67
     italian
    0.63
     italy
    0.63
    celotti
    0.59
     Italians
    0.58
    italian
    0.57
     Itália
    0.56
    Activations Density 0.270%

    No Known Activations