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-2-9B-IT
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 15527
    Prev
    Next
    INDEX
    Explanations

    asynchronous function calls and their defining structures in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code, punctuation, or start of turn

    np_acts-logits-general · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pinulongan
    -0.52
    Tembelea
    -0.36
     referenties
    -0.35
     للمعارف
    -0.34
    HasAnnotation
    -0.34
     هما
    -0.34
    ioutil
    -0.33
    ộng
    -0.33
    elemField
    -0.33
    。(
    -0.32
    POSITIVE LOGITS
    (()
    0.86
     ()
    0.83
    ={()
    0.83
    =()
    0.79
     (()
    0.75
     Runnable
    0.72
    =()=>{
    0.68
    :^{
    0.64
     ():
    0.61
    ()
    0.61
    Activations Density 0.095%

    No Known Activations