© 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 - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 10606
    Prev
    Next
    INDEX
    Explanations

    references to various types of offices and office-related terminology

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

    "office"

    np_acts-logits-general · gemini-2.0-flash

    office and its contexts

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    Cuándo
    -0.49
     bVar
    -0.46
     Cataluña
    -0.45
     promocional
    -0.44
     étr
    -0.43
     Marín
    -0.42
    łaś
    -0.41
     raisonnable
    -0.41
    dinosaur
    -0.41
     Künst
    -0.40
    POSITIVE LOGITS
    Office
    1.06
    office
    1.03
     OFFICE
    1.03
     Office
    1.02
     office
    0.98
     Offices
    0.95
    OFFICE
    0.93
     offices
    0.86
     OFFICES
    0.82
     Offic
    0.77
    Activations Density 0.034%

    No Known Activations