© 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. 18-GEMMASCOPE-RES-16K
    11. 8925
    Prev
    Next
    INDEX
    Explanations

    financial terms related to cost management and profitability

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

    Profit margins, studies, or RNA

    np_acts-logits-general · gemini-2.0-flash

    profit margin

    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
    anter
    -0.46
    awy
    -0.45
     radon
    -0.44
    olished
    -0.43
    bouncycastle
    -0.42
    ouden
    -0.41
    iante
    -0.40
     MERCHANTABILITY
    -0.40
     HAV
    -0.40
    ontes
    -0.40
    POSITIVE LOGITS
     margins
    1.32
     margin
    1.20
     profitability
    1.07
     Margin
    1.06
    Margins
    1.01
    margins
    0.98
    margin
    0.97
     profit
    0.96
    profit
    0.95
     Profit
    0.94
    Activations Density 0.136%

    No Known Activations