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. 18-GEMMASCOPE-RES-16K
    6. 1038
    Prev
    Next
    INDEX
    Explanations

    terms related to property descriptions and real estate features

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

    Apartments, condominiums, and HOAs

    np_acts-logits-general · gemini-2.0-flash

    apartments and condominiums

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     snippetHide
    -0.92
    IntoConstraints
    -0.82
     disambiguazione
    -0.79
    $_['
    -0.73
    脚注の使い方
    -0.63
    WebServlet
    -0.63
     Normdatei
    -0.61
     nahilalakip
    -0.59
    makeConstraints
    -0.56
     nationales
    -0.56
    POSITIVE LOGITS
     Residents
    1.06
     residents
    1.04
    Residents
    1.00
     resident
    1.00
     Resident
    0.98
     condominium
    0.92
     communal
    0.91
    Resident
    0.89
     condo
    0.85
     HOA
    0.83
    Activations Density 0.112%

    No Known Activations