Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 10509
    Prev
    Next
    INDEX
    Explanations

    phrases related to real estate transactions and negotiations

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

    after "of", "to", "the", "and"

    np_acts-logits-general · gemini-2.0-flash

    buyer and seller transactions

    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
    hdys
    -0.55
     canteen
    -0.53
    Activités
    -0.51
    transQ
    -0.49
     parli
    -0.48
     rechange
    -0.48
     NDEBUG
    -0.47
     abrasion
    -0.47
     alimentation
    -0.47
    ystema
    -0.46
    POSITIVE LOGITS
     Buyers
    1.09
     buyers
    1.08
     buyer
    1.07
    Buyers
    1.01
     Buyer
    0.99
     sellers
    0.97
     seller
    0.97
    buyers
    0.95
     Seller
    0.93
    buyer
    0.92
    Activations Density 0.221%

    No Known Activations