© 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-2-9B
    4. Residual Stream - 16k
    5. 7-GEMMASCOPE-RES-16K
    6. 15741
    Prev
    Next
    INDEX
    Explanations

    references to the concept of expense

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    matchCondition
    -0.66
    ########.
    -0.57
     Ueb
    -0.57
    daß
    -0.44
     artig
    -0.44
    ImageContext
    -0.44
     jspb
    -0.42
    ViewInit
    -0.41
    RTEE
    -0.41
    toggler
    -0.41
    POSITIVE LOGITS
     expensive
    2.03
    expensive
    1.95
     Expensive
    1.83
    Expensive
    1.81
     costly
    1.75
     pricey
    1.54
     дорого
    1.27
     teuer
    1.20
     cheaper
    1.17
     caros
    1.17
    Activations Density 0.128%

    No Known Activations