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. 24-GEMMASCOPE-RES-16K
    6. 4434
    Prev
    Next
    INDEX
    Explanations

    references to technical concepts related to cryptocurrencies and peer-to-peer networking

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Bitcoin, cryptocurrency, or digital wallets

    np_acts-logits-general · gemini-2.0-flash

    Bitcoin and cryptocurrency names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    出版年
    -0.99
    +#+#
    -0.67
     EClass
    -0.61
     AssemblyVersion
    -0.53
    GOTREF
    -0.53
     GIPHY
    -0.53
    FieldBuilder
    -0.51
    enuta
    -0.50
    invokeLater
    -0.50
     carousel
    -0.50
    POSITIVE LOGITS
     wallet
    0.70
     spending
    0.63
     Bitcoin
    0.62
     Wallet
    0.58
    TypedDataSet
    0.58
     wallets
    0.57
     spend
    0.57
     Spending
    0.56
     Tor
    0.56
     spent
    0.55
    Activations Density 0.116%

    No Known Activations