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. 10-GEMMASCOPE-RES-16K
    6. 2815
    Prev
    Next
    INDEX
    Explanations

    specific mathematical symbols and terms related to functions or equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Barclay
    -0.93
     विश्वसनीयता
    -0.93
    setVerticalGroup
    -0.92
     Shira
    -0.86
     prv
    -0.84
     الرياضيه
    -0.84
     Cakes
    -0.84
     Dempsey
    -0.83
     Pagoda
    -0.83
     quran
    -0.82
    POSITIVE LOGITS
    WriteLiteral
    0.77
    ════════
    0.75
    //
    0.71
     hat
    0.71
    hat
    0.69
    )="
    0.69
    Rode
    0.68
     Rode
    0.68
     hats
    0.66
    %"
    0.65
    Activations Density 0.997%

    No Known Activations