© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 13732
    Prev
    Next
    INDEX
    Explanations

    system-related classes and properties in coding contexts, particularly those used in GUI frameworks

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

    Values assigned in GUI/UI code

    np_acts-logits-general · gemini-2.0-flash

    System.Windows.Forms/JSeparator/sf::Style/PDO

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    FailureListener
    -0.51
    onAttach
    -0.50
    ("
    -0.50
    ('
    -0.49
     D
    -0.48
    (
    -0.48
    {
    -0.47
     S
    -0.47
    @
    -0.46
    abro
    -0.46
    POSITIVE LOGITS
     beginnetje
    0.90
    styleType
    0.81
    ſelf
    0.75
    DebuggerNonUser
    0.74
    HtmlAttribute
    0.73
     الرياضيه
    0.72
     виправивши
    0.71
     pleaſure
    0.70
    webElementXpaths
    0.68
    ientras
    0.68
    Activations Density 0.020%

    No Known Activations