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. 6279
    Prev
    Next
    INDEX
    Explanations

    instances of the word "but" and expressions indicating contrast or opposition

    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
     and
    -0.65
    FundMe
    -0.56
    Autoritní
    -0.55
    فایل‌لار
    -0.54
    SneakyThrows
    -0.52
     วัด
    -0.51
    siella
    -0.51
    zerű
    -0.49
    mäßigen
    -0.49
    colns
    -0.49
    POSITIVE LOGITS
     And
    1.47
    And
    1.34
     But
    1.23
    But
    1.13
     Però
    0.85
     Nhưng
    0.85
     So
    0.81
     Yet
    0.80
    HomeAsUpEnabled
    0.80
     مشين
    0.77
    Activations Density 0.266%

    No Known Activations