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. 24-GEMMASCOPE-RES-16K
    6. 13985
    Prev
    Next
    INDEX
    Explanations

    terminology related to legal and rental agreements

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

    Rental agreements and tenant occupancy

    np_acts-logits-general · gemini-2.0-flash

    rental lease agreements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     disambiguazione
    -0.77
    RectangleBorder
    -0.71
    UIControlState
    -0.61
    ConstraintMaker
    -0.61
    findpost
    -0.58
     medals
    -0.55
    expandindo
    -0.54
    ⓘ
    -0.52
    GEBURTSDATUM
    -0.52
     EClass
    -0.52
    POSITIVE LOGITS
     tenants
    1.98
     tenant
    1.97
     rent
    1.86
     Tenants
    1.67
     Tenant
    1.67
     lease
    1.67
     Rent
    1.63
     rents
    1.60
     tenancy
    1.59
     rental
    1.58
    Activations Density 0.179%

    No Known Activations