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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 9516
    Prev
    Next
    INDEX
    Explanations

    references to Europe and its political or geographical context

    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
    RenderAtEndOf
    -0.85
     BitSet
    -0.77
    ConstraintMaker
    -0.76
     STC
    -0.70
     TCS
    -0.70
    JspWriter
    -0.69
     geslacht
    -0.69
    TDS
    -0.69
     Pila
    -0.69
     Sdn
    -0.69
    POSITIVE LOGITS
     Europe
    1.49
     European
    1.38
     Europa
    1.33
    Europe
    1.32
    European
    1.25
     Europeans
    1.24
    EUROPE
    1.20
    Europa
    1.19
     Europea
    1.18
     EUROPE
    1.17
    Activations Density 0.050%

    No Known Activations