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. 3-GEMMASCOPE-RES-16K
    6. 16232
    Prev
    Next
    INDEX
    Explanations

    financial metrics and stock market performance indicators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Naturs
    -0.54
     O
    -0.53
     Walsh
    -0.52
    InlineData
    -0.51
    려
    -0.47
    ország
    -0.46
    isième
    -0.45
    říve
    -0.45
    windowFixed
    -0.44
    слава
    -0.44
    POSITIVE LOGITS
    ASX
    1.02
     FTSE
    0.96
     itſelf
    0.90
     bourse
    0.85
     Nasdaq
    0.84
     ASX
    0.84
     Stocks
    0.83
     stocks
    0.83
    utilisons
    0.81
    Shares
    0.80
    Activations Density 0.520%

    No Known Activations