© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 104
    Prev
    Next
    INDEX
    Explanations

    code-related actions related to button interactions in JavaFX applications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WireFormatLite
    -0.85
    UrlResolution
    -0.67
    mergeFrom
    -0.65
    CodedInputStream
    -0.64
    AccessorTable
    -0.62
     django
    -0.58
     yii
    -0.55
    TagHelper
    -0.54
    OGND
    -0.54
     Lumpur
    -0.54
    POSITIVE LOGITS
     javafx
    1.18
    FXML
    1.14
    fxml
    0.96
    FX
    0.89
    Scene
    0.89
     FX
    0.88
    FXMLLoader
    0.87
    Stage
    0.85
    scene
    0.84
     Scene
    0.81
    Activations Density 0.068%

    No Known Activations