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. 31-GEMMASCOPE-RES-16K
    6. 15424
    Prev
    Next
    INDEX
    Explanations

    specific geographical locations and names associated with Romania and Romanian culture

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

    Romanian words or names

    np_acts-logits-general · gemini-2.0-flash

    Romanian places and names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     argint
    -0.88
     picioare
    -0.77
    šanai
    -0.73
     ragaz
    -0.71
     uș
    -0.69
     viață
    -0.69
     maș
    -0.69
     peuples
    -0.65
     păr
    -0.65
     stanga
    -0.62
    POSITIVE LOGITS
     Romanian
    0.94
     Romania
    0.79
     Bucharest
    0.76
     متعلقه
    0.69
    Romania
    0.66
    ulescu
    0.65
     Nicolae
    0.64
     Cluj
    0.63
     Mihai
    0.62
     Radu
    0.62
    Activations Density 0.031%

    No Known Activations