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. 4-GEMMASCOPE-RES-16K
    6. 742
    Prev
    Next
    INDEX
    Explanations

    LaTeX commands and mathematical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BagConstraints
    -0.91
     postIndex
    -0.90
    IsContent
    -0.84
    setVerticalGroup
    -0.83
    AsUp
    -0.76
     themſelves
    -0.75
     Lepto
    -0.74
     Jefus
    -0.74
     itſelf
    -0.72
    CloseOperation
    -0.71
    POSITIVE LOGITS
    mathrm
    1.04
     mathvariant
    0.55
    mathbf
    0.53
    WEBPACK
    0.52
    '])){
    
    0.51
    ();*/
    0.50
     ***!
    0.50
    pyx
    0.49
     an
    0.48
    ]))
    
    0.46
    Activations Density 0.078%

    No Known Activations