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. 5-GEMMASCOPE-RES-16K
    6. 13346
    Prev
    Next
    INDEX
    Explanations

    occurrences of the term "exchange" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    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
    -0.81
    nitus
    -0.73
    Prim
    -0.72
     Primrose
    -0.72
     nationaux
    -0.69
    дото
    -0.67
     propof
    -0.67
     digress
    -0.67
     recrutement
    -0.66
     rosary
    -0.65
    POSITIVE LOGITS
     exchange
    2.76
     Exchange
    2.67
    exchange
    2.54
    Exchange
    2.53
     exchanges
    2.51
     EXCHANGE
    2.48
     exchanged
    2.33
     Exchanges
    2.22
    EXCHANGE
    2.12
     exchanging
    2.10
    Activations Density 0.061%

    No Known Activations