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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 8-GEMMASCOPE-RES-16K
    11. 10887
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "home" and related returning actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    awtextra
    -0.87
     propOrder
    -0.80
     autorytatywna
    -0.65
    #+#
    -0.64
    ImageContext
    -0.62
    */),
    -0.62
     estimés
    -0.60
    rrggbb
    -0.60
     ویکی‌پدیا
    -0.60
    Personendaten
    -0.59
    POSITIVE LOGITS
     home
    1.13
     hjem
    1.00
    home
    0.96
     HOME
    0.96
     thuis
    0.94
     Home
    0.93
     homeward
    0.91
    Home
    0.90
     hometown
    0.85
     pulang
    0.85
    Activations Density 0.202%

    No Known Activations