© 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. 22-GEMMASCOPE-RES-16K
    6. 16381
    Prev
    Next
    INDEX
    Explanations

    code related to user interface elements and event handling in a Windows Forms application

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PropertyChanging
    -0.50
    Donnell
    -0.49
     AssemblyTitle
    -0.49
    onAttach
    -0.46
    quill
    -0.46
    QName
    -0.45
    mple
    -0.45
    ம்ப
    -0.45
    #[
    -0.45
    PyTuple
    -0.45
    POSITIVE LOGITS
    AnchorStyles
    0.81
     beginnetje
    0.80
    extAlignment
    0.80
    DockStyle
    0.79
     Shakspeare
    0.71
     propOrder
    0.68
    setVerticalGroup
    0.67
     Мексичка
    0.65
     poffe
    0.61
     Houſe
    0.61
    Activations Density 0.097%

    No Known Activations