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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 35-GEMMASCOPE-RES-16K
    6. 7321
    Prev
    Next
    INDEX
    Explanations

    references to home-related experiences and sentiments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    XmlAccessType
    -0.45
    出版年
    -0.35
     leksikon
    -0.27
    ory
    -0.26
    upuncture
    -0.26
     †
    -0.25
    DMETHOD
    -0.25
    ViewImports
    -0.25
    lichem
    -0.25
     العرب
    -0.24
    POSITIVE LOGITS
     home
    3.55
    home
    2.81
     thuis
    2.66
     HOME
    2.64
    Home
    2.55
     Home
    2.50
     hjemme
    2.50
    HOME
    2.48
     zuhause
    2.27
     otthon
    2.22
    Activations Density 0.598%

    No Known Activations