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-2-2B
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 6574
    Prev
    Next
    INDEX
    Explanations

    references to Russia and its political figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     NDEBUG
    -0.66
    =$?
    -0.63
     ")");
    -0.63
     Diſ
    -0.62
     المبار
    -0.61
     itſelf
    -0.60
    อ้างอิง
    -0.59
    šanai
    -0.59
     fufficient
    -0.59
     ovation
    -0.58
    POSITIVE LOGITS
     hem
    1.03
    hem
    0.84
     Russian
    0.80
     Russia
    0.77
    Russian
    0.77
    XmlEnum
    0.77
    новниш
    0.75
     Hem
    0.72
     Justice
    0.71
    Hem
    0.70
    Activations Density 0.119%

    No Known Activations