© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 4159
    Prev
    Next
    INDEX
    Explanations

    specific terms related to real estate transactions and their processes

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

    Real estate transactions related to buyers and sellers

    np_acts-logits-general · gemini-2.0-flash

    seller/buyer transactions

    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
    wieś
    -0.60
    verwijspagina
    -0.57
    cookieParser
    -0.56
    multer
    -0.55
     disambiguazione
    -0.54
     Вікі
    -0.52
    gerät
    -0.51
    migrationBuilder
    -0.51
    rophoresis
    -0.51
    Bioaccumulative
    -0.51
    POSITIVE LOGITS
     seller
    1.19
     sellers
    1.14
     buyers
    1.11
     buyer
    1.10
     Seller
    1.08
     closing
    1.05
     Buyers
    1.03
     Sellers
    1.02
    Seller
    1.00
    Buyers
    1.00
    Activations Density 0.174%

    No Known Activations