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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 21-GEMMASCOPE-RES-16K
    6. 1942
    Prev
    Next
    INDEX
    Explanations

    data structures and financial terms related to amounts and currencies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    jois
    -0.53
    Nome
    -0.46
     tè
    -0.45
    Contato
    -0.44
    :✨
    -0.43
     clave
    -0.43
    agine
    -0.43
     restre
    -0.43
     vocales
    -0.42
     clé
    -0.42
    POSITIVE LOGITS
     money
    1.08
     monetary
    1.07
     dollars
    1.06
     amount
    0.97
     dollar
    0.96
    money
    0.93
    amount
    0.91
     monies
    0.90
     cents
    0.90
     price
    0.90
    Activations Density 0.126%

    No Known Activations