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. 16242
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and structural elements typical in scientific or technical writings

    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
     primeiras
    -0.81
     first
    -0.80
     eerste
    -0.79
     primeira
    -0.76
     ensimmä
    -0.73
     pertama
    -0.73
     Wicidata
    -0.73
     første
    -0.72
     пър
    -0.72
     primeiros
    -0.71
    POSITIVE LOGITS
     third
    0.80
     fourth
    0.75
    ③
    0.73
     second
    0.71
    ②
    0.69
     Thirdly
    0.68
    third
    0.66
    ④
    0.65
    第三
    0.64
     iii
    0.62
    Activations Density 3.249%

    No Known Activations