© 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. 22-GEMMASCOPE-RES-16K
    11. 3483
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal transactions and agreements, particularly those involving plea deals and exchanges

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

    "...in exchange for..."

    np_acts-logits-general · gemini-2.0-flash

    offer in exchange

    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
     surla
    -0.55
    WebServlet
    -0.54
    addError
    -0.51
    endpush
    -0.51
    siapkan
    -0.49
    anstalt
    -0.49
    原始内容存档于
    -0.48
     finition
    -0.46
     Gok
    -0.46
     NKC
    -0.46
    POSITIVE LOGITS
     exchange
    3.55
    exchange
    3.15
     exchanged
    3.05
     Exchange
    3.04
     exchanges
    2.95
     exchanging
    2.93
    Exchange
    2.91
     EXCHANGE
    2.88
     swap
    2.58
     Exchanges
    2.57
    Activations Density 0.371%

    No Known Activations