© 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. 18-GEMMASCOPE-RES-16K
    11. 8954
    Prev
    Next
    INDEX
    Explanations

    phrases related to workplace procedures and employee interactions

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

    "At" followed by workplace-related words

    np_acts-logits-general · gemini-2.0-flash

    at work

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     onAnimation
    -0.60
    曖昧さ回避
    -0.55
    ertos
    -0.54
     wireType
    -0.51
     CreateTagHelper
    -0.50
    Espèce
    -0.49
    QtGui
    -0.46
     charset
    -0.46
    زيون
    -0.46
     stør
    -0.45
    POSITIVE LOGITS
     workplace
    1.66
     work
    1.43
     Workplace
    1.39
     workplaces
    1.39
     office
    1.25
    work
    1.24
    Work
    1.15
    Workplace
    1.15
     WORK
    1.12
    office
    1.12
    Activations Density 0.189%

    No Known Activations