© 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. 4-GEMMASCOPE-RES-16K
    11. 2922
    Prev
    Next
    INDEX
    Explanations

    programming constructs related to user interface elements and their properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    __':
    -0.59
    NewUrlParser
    -0.53
    queryInterface
    -0.52
     betweenstory
    -0.52
     AssemblyCompany
    -0.52
    DrawerToggle
    -0.51
    GEBURTSDATUM
    -0.51
    __":
    -0.50
    cambrian
    -0.49
    vatar
    -0.49
    POSITIVE LOGITS
    SerializeField
    1.15
    IBOutlet
    1.04
     IBOutlet
    0.89
    FXML
    0.87
     تضيفلها
    0.73
    ViewChild
    0.73
    ToScroll
    0.66
    ContentAsync
    0.63
    labelControl
    0.57
    parsedMessage
    0.55
    Activations Density 0.061%

    No Known Activations