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. 3596
    Prev
    Next
    INDEX
    Explanations

    terms related to financial products and regulatory agencies

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

    Cryptocurrency exchanges and trading

    np_acts-logits-general · gemini-2.0-flash

    cryptocurrency and exchange 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
    abestanden
    -0.63
    GeneratedValue
    -0.60
    évaluateur
    -0.55
    MemoryWarning
    -0.55
    
    -0.55
    cshtml
    -0.55
    ContentAsync
    -0.54
    Content
    -0.54
    content
    -0.53
     NSCoder
    -0.52
    POSITIVE LOGITS
     exchange
    0.99
     Exchange
    0.94
     exchanges
    0.93
    exchange
    0.89
    Exchange
    0.89
     exchanging
    0.84
     Exchanges
    0.83
     EXCHANGE
    0.81
     exchanged
    0.77
     traded
    0.77
    Activations Density 0.062%

    No Known Activations