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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 6-GEMMASCOPE-RES-16K
    6. 6229
    Prev
    Next
    INDEX
    Explanations

    the word "or" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Saltar
    -0.74
     tric
    -0.74
     ―――――
    -0.73
     Shakspeare
    -0.72
    ิมพ์
    -0.69
    neſs
    -0.69
     Weyl
    -0.69
     cocco
    -0.68
     karte
    -0.68
     fubject
    -0.68
    POSITIVE LOGITS
     or
    1.65
     atau
    1.46
     eller
    1.45
     یا
    1.43
     Or
    1.42
    หรือ
    1.37
     oder
    1.36
     или
    1.33
     OR
    1.31
    或者
    1.29
    Activations Density 0.237%

    No Known Activations