© 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-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 84699
    Prev
    Next
    INDEX
    Explanations

    various forms of the word "work"

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

    work out

    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
     cadeia
    -0.61
    sidemargin
    -0.59
     pingente
    -0.59
    ʚ
    -0.56
     아니라
    -0.56
    istoitu
    -0.53
     vaguely
    -0.52
    orghini
    -0.52
     capuz
    -0.51
     mídia
    -0.50
    POSITIVE LOGITS
    Work
    1.13
     Work
    1.04
    work
    1.04
     work
    1.01
    WORK
    0.93
     WORK
    0.90
    travail
    0.78
     trabajo
    0.78
     Trabajo
    0.74
    working
    0.73
    Activations Density 0.059%

    No Known Activations