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 - 65k
    5. 12-GEMMASCOPE-RES-65K
    6. 36505
    Prev
    Next
    INDEX
    Explanations

    references to oak and holly trees

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tonsoft
    -0.93
     Granger
    -0.90
     Beni
    -0.85
    /*
    -0.78
     Whoever
    -0.76
    ViewType
    -0.76
    fillText
    -0.76
    Pert
    -0.75
    kaitan
    -0.75
     Pert
    -0.75
    POSITIVE LOGITS
     Oak
    1.56
    Oak
    1.46
     oak
    1.39
    oak
    1.28
     OAK
    1.27
    OAK
    1.24
     oaks
    0.98
     Oakley
    0.98
     Quercus
    0.96
     Oaks
    0.94
    Activations Density 0.009%

    No Known Activations