Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 10006
    Prev
    Next
    INDEX
    Explanations

    mentions of administrative or legal challenges related to labor issues

    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
     snippetHide
    -1.03
    principalColumn
    -0.87
    SBATCH
    -0.79
     Савезне
    -0.71
     relâche
    -0.69
    IsContent
    -0.69
    {
    
    
    -0.69
    期刊论文
    -0.68
     Efq
    -0.68
     pinulongan
    -0.68
    POSITIVE LOGITS
    llium
    0.59
    setImageResource
    0.59
    RegressionTest
    0.54
    squareup
    0.52
    неопр
    0.52
    DNEY
    0.52
    setHas
    0.51
    CUSS
    0.51
    gypten
    0.51
    ustris
    0.51
    Activations Density 4.486%

    No Known Activations