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. 14133
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions involving mappings and variable constraints

    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
     Ash
    -0.51
     Bis
    -0.48
     live
    -0.46
    Hentet
    -0.45
    Live
    -0.45
    frutar
    -0.43
     Tri
    -0.43
     Pro
    -0.43
    ={()
    -0.43
    listFiles
    -0.43
    POSITIVE LOGITS
    SharedCtor
    0.83
     resourceCulture
    0.83
    principalTable
    0.78
     BrowserModule
    0.74
     AssemblyCompany
    0.72
    RTGC
    0.68
    sendRedirect
    0.67
     NotImplemented
    0.66
    URLException
    0.65
    Diwedd
    0.65
    Activations Density 1.765%

    No Known Activations