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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 11-GEMMASCOPE-RES-16K
    6. 5840
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "exchange" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     carburant
    -0.94
    ainville
    -0.77
    parseColor
    -0.77
     nationaux
    -0.74
    celotti
    -0.73
    cetin
    -0.73
    iverr
    -0.73
     defStyleAttr
    -0.72
     Voldemort
    -0.71
    nitus
    -0.71
    POSITIVE LOGITS
     exchanges
    1.86
     Exchange
    1.85
     exchange
    1.77
     EXCHANGE
    1.74
    Exchange
    1.72
    exchange
    1.69
     Exchanges
    1.66
     exchanged
    1.54
    EXCHANGE
    1.48
     exchanging
    1.39
    Activations Density 0.053%

    No Known Activations