© 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-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 8275
    Prev
    Next
    INDEX
    Explanations

    terms related to maintenance and operation of equipment

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

    the word "maintenance"

    np_acts-logits-general · gemini-2.0-flash

    maintenance or upkeep

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelperRunner
    -0.74
    GEBURTSDATUM
    -0.72
    awtextra
    -0.61
    SourceChecksum
    -0.59
    rollment
    -0.50
    memberOf
    -0.48
     FetchType
    -0.47
    yargs
    -0.47
    BackStack
    -0.46
     groupBox
    -0.46
    POSITIVE LOGITS
     maintenance
    2.83
     Maintenance
    2.47
    maintenance
    2.46
    Maintenance
    2.44
     MAINTENANCE
    2.22
     upkeep
    2.20
     mainten
    2.07
     maint
    2.02
     mantenimiento
    2.02
    MAINTENANCE
    2.00
    Activations Density 0.305%

    No Known Activations