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. 5-GEMMASCOPE-RES-16K
    6. 9848
    Prev
    Next
    INDEX
    Explanations

    syntax related to code documentation and annotations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    thâu
    -0.89
    MessageOf
    -0.84
     Theſe
    -0.83
     itſelf
    -0.79
     ―――――
    -0.76
    NameInMap
    -0.74
     Conſ
    -0.73
     Aphrodite
    -0.73
     themſelves
    -0.69
    SourceChecksum
    -0.69
    POSITIVE LOGITS
    //
    0.61
    /*
    0.60
    #![
    0.56
    ///<
    0.55
    WEBPACK
    0.52
     ['$
    0.51
     <
    0.51
    volut
    0.50
    illeurs
    0.50
    <
    0.49
    Activations Density 0.028%

    No Known Activations