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. 20-GEMMASCOPE-RES-16K
    6. 8690
    Prev
    Next
    INDEX
    Explanations

    expressions of desire or wishful thinking

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    |}{
    -0.64
    //*[@
    -0.59
    клопе
    -0.57
    endmodule
    -0.56
    MergeFrom
    -0.54
    mailto
    -0.54
    }{*}{
    -0.54
     Manzan
    -0.54
     fiind
    -0.54
     necessários
    -0.53
    POSITIVE LOGITS
    wish
    1.07
     wish
    1.04
     Wish
    0.96
    Wish
    0.92
     WISH
    0.91
    WISH
    0.80
     wishes
    0.77
     Wishes
    0.76
     wishing
    0.75
     wished
    0.74
    Activations Density 0.038%

    No Known Activations