Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 20-GEMMASCOPE-RES-65K
    6. 524
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and line breaks in the text

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

    programming code and class declarations

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

    .NET MVC management INTERVIEWS Leonard

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     الاطلاع
    -0.66
    verifyException
    -0.63
    ยนต์
    -0.58
    classpath
    -0.58
    ArrowToggle
    -0.57
    tahui
    -0.54
    elemField
    -0.53
     jadx
    -0.53
    ParallelGroup
    -0.52
    TextBoxColumn
    -0.51
    POSITIVE LOGITS
    Mvc
    0.73
     COE
    0.62
    ']>
    0.61
     useAppContext
    0.60
     Normdatei
    0.59
    ueger
    0.59
    MENAFN
    0.58
     Qar
    0.58
     Tartar
    0.58
    MLLoader
    0.56
    Activations Density 0.001%

    No Known Activations