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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 30-GEMMASCOPE-RES-16K
    6. 10863
    Prev
    Next
    INDEX
    Explanations

    references to specific locations and community involvement in various initiatives

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

    French-Canadian locations or language

    np_acts-logits-general · gemini-2.0-flash

    Québec City and Montreal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     recognisable
    -0.66
     programmes
    -0.65
     recognised
    -0.64
     recognise
    -0.63
    alised
    -0.63
     Whilst
    -0.61
    centre
    -0.61
     customised
    -0.60
    programme
    -0.60
     programme
    -0.60
    POSITIVE LOGITS
     Quebec
    0.73
     Montreal
    0.67
     québéco
    0.62
    Quebec
    0.62
    Montreal
    0.62
     Québec
    0.59
     Haitian
    0.56
     aluminum
    0.54
     computadoras
    0.51
    Aluminum
    0.49
    Activations Density 0.110%

    No Known Activations