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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 21-GEMMASCOPE-RES-16K
    6. 509
    Prev
    Next
    INDEX
    Explanations

    content related to real estate investments and properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RenderAtEndOf
    -0.69
    expandindo
    -0.69
     مرئيه
    -0.64
    httphttps
    -0.62
     الحره
    -0.62
    例文帳に追加
    -0.62
    +#+#
    -0.58
    ocardio
    -0.57
     وتسجيلات
    -0.56
     дописавши
    -0.54
    POSITIVE LOGITS
     commercial
    1.03
     leasing
    1.02
     lease
    0.96
     tenants
    0.93
     tenant
    0.93
     development
    0.92
    Commercial
    0.92
     developers
    0.91
     leases
    0.91
     developer
    0.90
    Activations Density 0.167%

    No Known Activations