Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 22-GEMMASCOPE-RES-16K
    6. 8439
    Prev
    Next
    INDEX
    Explanations

    references to rental agreements and various rental items or services

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

    Rental services and leasing

    np_acts-logits-general · gemini-2.0-flash

    renting or leasing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    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
    -0.88
     NSCoder
    -0.64
     MessageBoxIcon
    -0.57
    ngrx
    -0.55
     CreateTagHelper
    -0.55
    WriteAttribute
    -0.54
    :+:
    -0.54
    Espèce
    -0.54
     estimés
    -0.53
    expandindo
    -0.53
    POSITIVE LOGITS
     rental
    2.62
     renting
    2.34
     rentals
    2.32
     rent
    2.32
     Rental
    2.29
     rented
    2.25
    Rental
    2.12
    Rent
    2.12
     Rent
    2.08
    rental
    2.06
    Activations Density 0.109%

    No Known Activations