Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 12759
    Prev
    Next
    INDEX
    Explanations

    financial figures and terms related to revenue and income

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

    Financial revenues and income

    np_acts-logits-general · gemini-2.0-flash

    revenue or income

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
    Dimensões
    -0.44
     esquecer
    -0.42
     düğ
    -0.42
     impossível
    -0.41
     paard
    -0.39
     meisje
    -0.38
     megt
    -0.38
     Had
    -0.38
    zcze
    -0.38
     stubbornly
    -0.37
    POSITIVE LOGITS
     revenue
    1.03
    Revenue
    1.01
     Revenue
    0.98
    revenue
    0.98
     revenues
    0.91
     income
    0.88
    Income
    0.85
     Revenues
    0.85
     Income
    0.83
     INCOME
    0.82
    Activations Density 0.207%

    No Known Activations