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. 20-GEMMASCOPE-RES-16K
    6. 8657
    Prev
    Next
    INDEX
    Explanations

    the start of documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     '{@
    -0.53
    idist
    -0.52
    eph
    -0.49
    opard
    -0.47
    monials
    -0.47
    slidesPer
    -0.46
    Спољашње
    -0.45
    Спасылкі
    -0.44
     miglia
    -0.44
    šte
    -0.44
    POSITIVE LOGITS
     betweenstory
    0.82
    MessageOf
    0.77
    uegos
    0.74
     Himo
    0.73
    Jeografia
    0.72
    MLLoader
    0.70
     للاسماء
    0.70
    AndEndTag
    0.69
    
    0.69
    يكب
    0.68
    Activations Density 0.379%

    No Known Activations