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. 10-GEMMASCOPE-RES-16K
    6. 13287
    Prev
    Next
    INDEX
    Explanations

    concepts related to housing discrimination and legal issues surrounding tenants' rights

    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
     autorytatywna
    -0.67
    RectangleBorder
    -0.67
     للمعارف
    -0.57
     CreateTagHelper
    -0.53
     ""}
    -0.53
    rió
    -0.50
    kurs
    -0.50
    اما
    -0.48
     solde
    -0.48
     Courses
    -0.48
    POSITIVE LOGITS
     rental
    1.00
     tenants
    0.96
     renters
    0.94
     rentals
    0.92
     rent
    0.91
     renter
    0.87
     tenant
    0.87
     Rent
    0.85
    Rent
    0.85
     tenancy
    0.85
    Activations Density 0.094%

    No Known Activations