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 - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 65680
    Prev
    Next
    INDEX
    Explanations

    references to list boxes and user interface elements in programming

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

    listBox and list values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    webElementXpaths
    -0.74
     disambiguazione
    -0.72
    AddTagHelper
    -0.72
     propOrder
    -0.72
     يتيمه
    -0.72
     Picchu
    -0.71
     GenerationType
    -0.71
    makeConstraints
    -0.69
    ContentValues
    -0.68
    UnusedPrivate
    -0.67
    POSITIVE LOGITS
     list
    0.63
    ListActivity
    0.61
    listBox
    0.57
    ListBox
    0.52
     liste
    0.51
     lists
    0.50
     listing
    0.48
    list
    0.47
    ollectionView
    0.45
     List
    0.44
    Activations Density 0.018%

    No Known Activations