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 - 65k
    5. 16-GEMMASCOPE-RES-65K
    6. 53417
    Prev
    Next
    INDEX
    Explanations

    punctuation and quotation marks in the text

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

    mathematical symbols and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     utafitiHapana
    -0.68
     المعيارى
    -0.64
    存于互联网档案馆
    -0.60
     kasarigan
    -0.57
     BoxFit
    -0.56
    errHandler
    -0.56
     ModelExpression
    -0.56
    FTS
    -0.55
    adaptiveStyles
    -0.54
     Blink
    -0.53
    POSITIVE LOGITS
    verwijspagina
    0.76
    页面存档备份
    0.75
    stateProvider
    0.65
     "..\..\..\
    0.65
    Initializable
    0.64
     vecchi
    0.63
    dafx
    0.62
    queryInterface
    0.62
    Šaltiniai
    0.61
    XmlAccessType
    0.60
    Activations Density 1.232%

    No Known Activations