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. 10250
    Prev
    Next
    INDEX
    Explanations

    mentions of "client" in various contexts related to software or services

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "client" or "clients"

    np_acts-logits-general · gemini-2.0-flash

    client, clients, client base

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    verwijspagina
    -0.85
    NameInMap
    -0.83
     ویکی‌پدی
    -0.79
    saraba
    -0.78
    webElementXpaths
    -0.74
    testify
    -0.73
     EdgeInsets
    -0.71
    ValueStyle
    -0.71
    SBATCH
    -0.70
    
    -0.69
    POSITIVE LOGITS
     getClient
    0.97
     clients
    0.95
     Clients
    0.89
    clients
    0.85
    Clients
    0.83
     CLIENT
    0.74
     clientId
    0.67
     client
    0.67
     Client
    0.64
    getClient
    0.64
    Activations Density 0.053%

    No Known Activations