© 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. 4-GEMMASCOPE-RES-16K
    6. 512
    Prev
    Next
    INDEX
    Explanations

    instructions or items related to tasks and to-do lists

    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
    Personendaten
    -0.73
     estekak
    -0.66
    MemoryWarning
    -0.64
     &___
    -0.59
    PerformLayout
    -0.56
    windowFixed
    -0.56
     copertura
    -0.53
    hObject
    -0.52
    /******/
    -0.50
    endphp
    -0.50
    POSITIVE LOGITS
     ToDo
    1.06
    todo
    0.99
    ToDo
    0.97
     Todo
    0.95
    Todo
    0.92
     todo
    0.84
     tasks
    0.83
    TodoList
    0.83
     Tasks
    0.82
    toDo
    0.79
    Activations Density 0.429%

    No Known Activations