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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 15441
    Prev
    Next
    INDEX
    Explanations

    percentages related to financial metrics regarding companies

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

    company revenue or turnover

    np_acts-logits-general · gemini-2.0-flash

    company revenue and turnover

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tvguidetime
    -0.73
    +#+
    -0.69
     Abp
    -0.65
    ThroughAttribute
    -0.65
     tartalomajánló
    -0.64
     ComVisible
    -0.64
     incontra
    -0.62
    +:+
    -0.62
     polaire
    -0.62
     Audiodateien
    -0.61
    POSITIVE LOGITS
     revenue
    1.23
     revenues
    1.16
     annual
    1.06
     gross
    1.01
    revenue
    0.96
     total
    0.94
     Gross
    0.89
    annual
    0.88
    Revenue
    0.86
     turnover
    0.86
    Activations Density 0.274%

    No Known Activations