© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 12-GEMMASCOPE-RES-16K
    11. 11554
    Prev
    Next
    INDEX
    Explanations

    concepts related to financial performance and profitability metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Voter
    -0.47
     kuu
    -0.46
     wsz
    -0.41
     diken
    -0.41
     commonwealth
    -0.39
     StringTokenizer
    -0.39
     trö
    -0.38
    Voter
    -0.38
    thar
    -0.38
     geschenk
    -0.37
    POSITIVE LOGITS
     profit
    1.05
    profit
    0.96
    Profit
    0.94
     profits
    0.94
     Profit
    0.94
     Profits
    0.85
    利润
    0.85
     profitability
    0.84
    profits
    0.82
     lucro
    0.72
    Activations Density 0.266%

    No Known Activations