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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 15941
    Prev
    Next
    INDEX
    Explanations

    XML or XML-like syntax elements, particularly related to class definitions and properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UnusedPrivate
    -0.46
    urlopen
    -0.46
     jScrollPane
    -0.45
     TextAlign
    -0.45
    LabelTagHelper
    -0.45
     RoutedEventArgs
    -0.43
    serviceWorker
    -0.43
    webElement
    -0.42
    ImageContext
    -0.42
    StackNavigator
    -0.41
    POSITIVE LOGITS
    новништво
    0.70
    PyExc
    0.67
    FromNib
    0.62
    Geplaatst
    0.61
     updateTime
    0.60
     grève
    0.58
    =$?
    0.58
    rubin
    0.58
    PMailer
    0.57
    مصادر
    0.57
    Activations Density 0.391%

    No Known Activations