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-2-2B
    4. Residual Stream - 16k
    5. 7-GEMMASCOPE-RES-16K
    6. 8798
    Prev
    Next
    INDEX
    Explanations

    references to ancient civilizations and cultures

    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
     initComponents
    -1.05
     myſelf
    -0.92
     становника
    -0.88
     purpoſe
    -0.85
     itſelf
    -0.83
    tvguidetime
    -0.82
     pleaſure
    -0.78
     obstante
    -0.76
     Jefus
    -0.76
     Theſe
    -0.76
    POSITIVE LOGITS
     Roman
    0.82
    Roman
    0.81
    Ancient
    0.78
     Greek
    0.78
     grecque
    0.75
     Ancient
    0.74
     ancient
    0.73
    Greek
    0.72
     greco
    0.68
    ancient
    0.67
    Activations Density 0.163%

    No Known Activations