© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 4-GEMMASCOPE-RES-16K
    11. 2031
    Prev
    Next
    INDEX
    Explanations

    references to menu items and selection actions in programming contexts

    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
     سكانية
    -0.77
    )?;
    -0.76
    ']){
    -0.74
    ()?;
    -0.70
    '>";
    -0.70
    GraphicsUnit
    -0.70
    ']);
    -0.69
     isComment
    -0.65
    ))){
    -0.64
    }]
    -0.64
    POSITIVE LOGITS
    MenuItem
    3.19
     MenuItem
    2.23
     JMenuItem
    1.35
    MenuItems
    1.24
    JMenuItem
    1.24
     menuItem
    1.10
    menuItem
    1.05
    ToolStripButton
    0.96
    jMenuItem
    0.89
    MenuButton
    0.89
    Activations Density 0.034%

    No Known Activations