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. 2-GEMMASCOPE-RES-16K
    6. 8423
    Prev
    Next
    INDEX
    Explanations

    formatting elements and syntactical structures in documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .
    -0.50
    Bbb
    -0.49
     
    -0.46
     in
    -0.45
     must
    -0.45
    huriyet
    -0.44
     plastic
    -0.44
     expressed
    -0.43
    궁
    -0.43
     $
    -0.43
    POSITIVE LOGITS
    tagHelperRunner
    0.81
     Monfieur
    0.79
     myſelf
    0.79
     auffi
    0.75
     leaſt
    0.73
     beginnetje
    0.72
    +:+
    0.72
     purpoſe
    0.71
     ſch
    0.71
    fjspx
    0.71
    Activations Density 0.954%

    No Known Activations