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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 5675
    Prev
    Next
    INDEX
    Explanations

    terms associated with prices and expenses, particularly emphasizing the comparison of price points and value

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     surla
    -1.04
    tvguidetime
    -0.86
    WebElementEntity
    -0.84
    Viited
    -0.83
    expandindo
    -0.81
    )"),
    -0.80
    TypedDataSet
    -0.78
    writeField
    -0.75
     AssemblyCulture
    -0.73
    InputBorder
    -0.72
    POSITIVE LOGITS
     expensive
    0.82
     caros
    0.71
    Expensive
    0.70
     Expensive
    0.69
    expensive
    0.66
     costly
    0.62
     pricey
    0.59
     premium
    0.53
     duur
    0.47
     chère
    0.47
    Activations Density 0.192%

    No Known Activations