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. 13928
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and notations

    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
    lig
    -0.57
    printStackTrace
    -0.51
     kea
    -0.51
     mahi
    -0.49
    cet
    -0.47
    态
    -0.46
    rade
    -0.46
     New
    -0.45
     life
    -0.43
    ..\
    -0.43
    POSITIVE LOGITS
    enumi
    0.89
     betweenstory
    0.80
    ">//
    0.80
     محفوظة
    0.79
     AssemblyTitle
    0.75
    IsContent
    0.74
     متعلقه
    0.72
    tonsoft
    0.71
    setVerticalGroup
    0.70
    polazione
    0.70
    Activations Density 0.377%

    No Known Activations