© 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. 3-GEMMASCOPE-RES-16K
    11. 12146
    Prev
    Next
    INDEX
    Explanations

    terms related to exchanges and exchange rates in economic discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nitus
    -0.78
    celotti
    -0.76
     carburant
    -0.72
    lgari
    -0.69
    дото
    -0.68
    zygous
    -0.68
    στι
    -0.67
     ujednoznacz
    -0.67
    }{||
    -0.65
    IPAC
    -0.65
    POSITIVE LOGITS
     exchange
    3.47
     Exchange
    3.39
    exchange
    3.20
    Exchange
    3.17
     EXCHANGE
    3.14
     exchanges
    3.07
     Exchanges
    2.75
     exchanged
    2.72
    EXCHANGE
    2.56
     exchanging
    2.48
    Activations Density 0.048%

    No Known Activations