© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 13-GEMMASCOPE-RES-65K
    11. 56219
    Prev
    Next
    INDEX
    Explanations

    keywords and elements related to the Kotlin programming language and Gradle build scripts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ChildScrollView
    -1.11
    Geplaatst
    -0.88
    MethodManager
    -0.86
    UserScript
    -0.84
     prisonniers
    -0.79
    ::_('
    -0.79
    posedge
    -0.75
     Nicky
    -0.75
    原始内容存档于
    -0.74
    Nicky
    -0.74
    POSITIVE LOGITS
     kotlin
    1.66
    kotlin
    1.64
     Kotlin
    1.19
    Kotlin
    1.01
    gradle
    0.76
     halting
    0.69
    urent
    0.67
    Wolverine
    0.66
     урна
    0.65
    Squad
    0.63
    Activations Density 0.025%

    No Known Activations