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. 14221
    Prev
    Next
    INDEX
    Explanations

    function definitions and calls in programming code

    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
     NSCoder
    -0.58
     (
    
    -0.58
    پیوند
    -0.58
    اق
    -0.56
     للمعارف
    -0.52
     equator
    -0.51
    ayaquil
    -0.49
    (
    
    -0.49
     populaires
    -0.47
    veratrol
    -0.47
    POSITIVE LOGITS
    ()
    0.96
    =()=>{
    0.91
    ();
    0.90
     ()
    0.79
    (){
    0.78
    ());
    0.78
    تقاوى
    0.75
    ]()
    0.74
    ())
    0.73
    =()
    0.73
    Activations Density 0.159%

    No Known Activations