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-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 16038
    Prev
    Next
    INDEX
    Explanations

    references to rental services and associated equipment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
    ConstraintMaker
    -0.70
     CreateTagHelper
    -0.64
    WebServlet
    -0.61
     MessageBoxIcon
    -0.60
    reportWebVitals
    -0.57
    ngrx
    -0.56
    tigs
    -0.54
     defaultstate
    -0.54
    addGap
    -0.53
    ogra
    -0.51
    POSITIVE LOGITS
     rental
    2.51
     renting
    2.29
     rentals
    2.26
     Rental
    2.24
     rented
    2.19
     rent
    2.13
    Rental
    2.03
    Rent
    2.02
    rental
    1.97
     Rent
    1.94
    Activations Density 0.136%

    No Known Activations