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. 20-GEMMASCOPE-RES-16K
    6. 7536
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to financial institutions and operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uxxxx
    -0.63
     Khrushchev
    -0.54
    sizeCache
    -0.53
    classID
    -0.50
    etano
    -0.49
     auger
    -0.49
    HRC
    -0.47
    Istorija
    -0.47
     affitto
    -0.47
     Johansson
    -0.47
    POSITIVE LOGITS
     banking
    2.04
     bank
    1.90
     Banking
    1.88
     banks
    1.83
    banking
    1.73
     Bank
    1.70
     banker
    1.69
     bankers
    1.69
    Banking
    1.68
     BANK
    1.66
    Activations Density 0.349%

    No Known Activations