© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 12939
    Prev
    Next
    INDEX
    Explanations

    references to organizational tools and productivity applications

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

    "Todo" or task-related apps or lists

    np_acts-logits-general · gemini-2.0-flash

    todo and task lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Glaub
    -0.42
     Мексичка
    -0.40
    RegistryLite
    -0.38
    IUrlHelper
    -0.35
    webElement
    -0.35
     grze
    -0.35
    ⤹
    -0.35
    WEBPACK
    -0.33
    UrlResolution
    -0.33
    håll
    -0.32
    POSITIVE LOGITS
     task
    0.83
     Tasks
    0.82
     tasks
    0.82
    Tasks
    0.78
     Task
    0.75
    task
    0.73
     todo
    0.73
     prioritizing
    0.73
    Task
    0.71
     priorities
    0.71
    Activations Density 0.198%

    No Known Activations