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. 10-GEMMASCOPE-RES-16K
    6. 13246
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "function."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IsMutable
    -0.98
    లాలు
    -0.97
     فريبيس
    -0.96
     itſelf
    -0.90
     OFDb
    -0.87
     resourceCulture
    -0.83
     Paglinawan
    -0.81
     ―――――
    -0.78
     Shakspeare
    -0.77
     himſelf
    -0.76
    POSITIVE LOGITS
    function
    0.93
     ActionResult
    0.86
    def
    0.79
     function
    0.71
     def
    0.68
    帖最后由
    0.67
    newcommand
    0.66
    ROUTINE
    0.65
    fn
    0.64
    ordnung
    0.60
    Activations Density 0.026%

    No Known Activations