© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 16271
    Prev
    Next
    INDEX
    Explanations

    phrases that involve transactions or exchanges, particularly related to payments, offers, and bargaining

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

    "In exchange for"

    np_acts-logits-general · gemini-2.0-flash

    in exchange for

    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
    ruptedException
    -0.57
     MonoBehaviour
    -0.54
    Viitteet
    -0.53
    
    -0.50
    日閲覧
    -0.50
    Parcelize
    -0.50
     dif
    -0.48
     Dif
    -0.48
    arote
    -0.48
    CPtr
    -0.46
    POSITIVE LOGITS
     exchange
    2.15
    exchange
    1.80
     exchanged
    1.74
     Exchange
    1.66
    Exchange
    1.60
     EXCHANGE
    1.57
     exchanges
    1.57
     exchanging
    1.55
     échange
    1.53
     trade
    1.45
    Activations Density 0.292%

    No Known Activations