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
    4. Residual Stream - 131k
    5. 32-GEMMASCOPE-RES-131K
    6. 130009
    Prev
    Next
    INDEX
    Explanations

    references to UI components in programming, specifically ImageViews and layout structures

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

    awe, roughly, [@B

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_32/width_131k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.32.hook_resid_post
    Hook Layer
    32
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vermelhas
    -0.55
     архивлан
    -0.54
    Carriera
    -0.52
    chargez
    -0.52
    twimg
    -0.51
     république
    -0.51
     Biôgrafia
    -0.49
     ſeinen
    -0.49
     zoude
    -0.49
     AttributeSet
    -0.49
    POSITIVE LOGITS
    <bos>
    0.52
    ️
    0.46
    存于互联网档案馆
    0.41
    WriteLiteral
    0.39
    toastr
    0.38
     препратки
    0.36
    ,\,\
    0.35
    mainPanel
    0.35
     клей
    0.34
    marginVertical
    0.34
    Activations Density 0.059%

    No Known Activations