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. 20-GEMMASCOPE-RES-131K
    6. 103246
    Prev
    Next
    INDEX
    Explanations

    programming or scripting language components, specifically related to HTML, CSS, JavaScript, and their functionalities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
    rachtet
    -0.51
    twimg
    -0.48
    protoimpl
    -0.46
     AssemblyCompany
    -0.46
    exitRule
    -0.45
     HttpNotFound
    -0.44
     intStringLen
    -0.44
     okuyayım
    -0.44
    akterysty
    -0.44
     Signalez
    -0.43
    POSITIVE LOGITS
     noDo
    0.52
    Portale
    0.51
    SourceChecksum
    0.49
    lyt
    0.44
     betweenstory
    0.43
    amous
    0.42
    togen
    0.41
    -------------</
    0.40
    チャン
    0.39
    bigsqcup
    0.39
    Activations Density 0.004%

    No Known Activations