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. 20-GEMMASCOPE-RES-16K
    6. 1504
    Prev
    Next
    INDEX
    Explanations

    function declarations and their associated parameters in programming-related text

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

    Kotlin code using map, filter, flatMap, and sort functions

    np_acts-logits-general · gemini-2.0-flash

    functional programming operations

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     مشين
    -0.58
    theless
    -0.56
     للمعارف
    -0.53
    出版年
    -0.52
    
    -0.51
     يتيمه
    -0.51
     eaten
    -0.50
     المعيارى
    -0.50
    jiet
    -0.50
    oa̍t
    -0.49
    POSITIVE LOGITS
     {
    1.07
     {
    
    0.79
     \{
    0.76
    {
    0.75
    \{
    0.69
     {(
    0.63
     {_
    0.61
     block
    0.60
     $\{
    0.59
    >{
    0.59
    Activations Density 0.154%

    No Known Activations