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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 18-GEMMASCOPE-RES-16K
    6. 1464
    Prev
    Next
    INDEX
    Explanations

    terms related to Bitcoin and its trading characteristics

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

    Bitcoin, cryptocurrency, or blockchain mentions

    np_acts-logits-general · gemini-2.0-flash

    Bitcoin and cryptocurrency trading

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    invokeLater
    -0.70
    EndGlobalSection
    -0.62
    ItemBackground
    -0.61
    FormTagHelper
    -0.58
    )_/¯
    -0.57
     Guel
    -0.56
     DVDs
    -0.55
    RTSC
    -0.55
     onPostExecute
    -0.55
    subpackage
    -0.55
    POSITIVE LOGITS
     blockchain
    1.13
     crypto
    1.07
     Crypto
    0.98
    Crypto
    0.90
     Bitcoin
    0.89
     Blockchain
    0.89
     cryptocurrency
    0.86
     decentralized
    0.86
    crypto
    0.83
     Ethereum
    0.81
    Activations Density 0.077%

    No Known Activations