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. 10-GEMMASCOPE-RES-16K
    6. 7398
    Prev
    Next
    INDEX
    Explanations

    names of people and organizations involved in creative or medical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Arab
    -0.39
    camel
    -0.39
    Höhe
    -0.38
     Aceh
    -0.35
    Abitanti
    -0.35
     咖
    -0.34
    Arab
    -0.34
     مخ
    -0.33
    Искәрмәләр
    -0.33
     đẹp
    -0.32
    POSITIVE LOGITS
     Maharashtra
    0.92
     Marathi
    0.88
    Maharashtra
    0.75
     Mumbai
    0.65
     Pune
    0.65
    Referències
    0.63
     Bombay
    0.58
    Pune
    0.58
    protoimpl
    0.57
    Mumbai
    0.57
    Activations Density 0.817%

    No Known Activations