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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 448
    Prev
    Next
    INDEX
    Explanations

    the word "working" and its variations, indicating a focus on work-related contexts or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     defaultstate
    -1.03
    QMetaType
    -0.93
     NSCoder
    -0.93
    URLException
    -0.92
    دانشنامهٔ
    -0.89
     تضيفلها
    -0.86
     GBIF
    -0.82
     abstrait
    -0.82
     rempliss
    -0.81
     yym
    -0.81
    POSITIVE LOGITS
     working
    3.00
     Working
    2.91
    Working
    2.86
     WORKING
    2.67
    working
    2.61
    WORKING
    2.50
     trabajando
    1.30
     operating
    1.20
     Arbeits
    1.18
     functioning
    1.13
    Activations Density 0.069%

    No Known Activations