© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 4561
    Prev
    Next
    INDEX
    Explanations

    financial figures and performance metrics

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

    Financial gains: net, profit, revenue

    np_acts-logits-general · gemini-2.0-flash

    profit and revenue

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    #+#
    -0.62
    DoubleQuotes
    -0.44
    kmal
    -0.43
     kun
    -0.41
    BeginInit
    -0.41
    breos
    -0.41
    zigen
    -0.40
    constru
    -0.40
    EndInit
    -0.39
     verte
    -0.39
    POSITIVE LOGITS
     revenue
    1.64
     revenues
    1.63
     profits
    1.50
     income
    1.46
    revenue
    1.44
     earnings
    1.35
    Revenue
    1.33
     profit
    1.33
     Revenues
    1.33
     revenus
    1.31
    Activations Density 0.213%

    No Known Activations