© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 54506
    Prev
    Next
    INDEX
    Explanations

    programming-related syntax elements, particularly those indicating tasks or actions in code

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

    go testing async tasks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     InputDecoration
    -0.70
    RegressionTest
    -0.66
    :✨
    -0.63
    SharedDtor
    -0.59
    曖昧さ回避
    -0.59
    SharedCtor
    -0.57
     تضيفلها
    -0.54
    rungsseite
    -0.51
    ArrowToggle
    -0.50
    évaluateur
    -0.50
    POSITIVE LOGITS
    awaiter
    0.56
    addTask
    0.54
    tableFuture
    0.49
     tasks
    0.48
    Tasks
    0.46
     Task
    0.46
     linkovi
    0.45
     Jobs
    0.44
    async
    0.44
     Promise
    0.44
    Activations Density 0.000%

    No Known Activations