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-2-2B
    4. Residual Stream - 16k
    5. 7-GEMMASCOPE-RES-16K
    6. 14937
    Prev
    Next
    INDEX
    Explanations

    terms associated with Cuba, communism, and geopolitical tensions in relation to North Korea

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Закон
    -0.45
    IBarButtonItem
    -0.43
    COUVER
    -0.41
    Pranala
    -0.40
    sel
    -0.40
     simply
    -0.40
    det
    -0.39
    SPJ
    -0.39
     d
    -0.38
     Aragón
    -0.38
    POSITIVE LOGITS
     Iran
    0.95
     Cuban
    0.95
     оригіналу
    0.95
    Cuban
    0.94
     Cuba
    0.92
     Havana
    0.91
    Cuba
    0.90
     Tehran
    0.89
     CreateTagHelper
    0.88
     дописавши
    0.88
    Activations Density 0.219%

    No Known Activations