© 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-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 1326
    Prev
    Next
    INDEX
    Explanations

    instances of the word "work" and its various forms, indicating a focus on employment, collaboration, and productivity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Aerosol
    -0.62
     Enfield
    -0.58
     Cessna
    -0.52
    пля
    -0.52
     hábito
    -0.51
    ệng
    -0.51
     Inflation
    -0.50
     ketones
    -0.49
    نص
    -0.49
     lixo
    -0.49
    POSITIVE LOGITS
     working
    0.97
    WORKING
    0.96
    Working
    0.95
     WORKING
    0.92
     worked
    0.89
     Working
    0.88
    working
    0.86
    worked
    0.86
     Worked
    0.84
    Worked
    0.82
    Activations Density 0.108%

    No Known Activations