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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 16225
    Prev
    Next
    INDEX
    Explanations

    phrases and names related to locations in Vietnam

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     enfans
    -0.86
     pleaſure
    -0.79
    yntaxException
    -0.74
     myſelf
    -0.73
    writeFieldEnd
    -0.70
     esternos
    -0.69
     المعيارى
    -0.68
     stanga
    -0.67
    ſelf
    -0.67
    NameInMap
    -0.66
    POSITIVE LOGITS
    swire
    0.40
     sau
    0.36
     tr
    0.34
     mang
    0.32
     spécifique
    0.31
    đ
    0.31
     trong
    0.31
     vía
    0.30
    cuado
    0.30
     Đ
    0.29
    Activations Density 0.016%

    No Known Activations