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-2-9B
    4. Residual Stream - 16k
    5. 36-GEMMASCOPE-RES-16K
    6. 14608
    Prev
    Next
    INDEX
    Explanations

    references to significant financial events and their impacts on the stock market

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    újo
    -0.50
    UnusedPrivate
    -0.43
    Notae
    -0.39
    WebServlet
    -0.39
    tagext
    -0.38
     тро
    -0.37
    cerely
    -0.35
    SequentialGroup
    -0.35
    izr
    -0.35
    unteer
    -0.35
    POSITIVE LOGITS
     investors
    1.97
     investor
    1.91
     stock
    1.70
     Investors
    1.66
    Investors
    1.63
     Investor
    1.59
    investors
    1.57
    investor
    1.55
     stocks
    1.55
    Investor
    1.49
    Activations Density 0.865%

    No Known Activations