© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 8704
    Prev
    Next
    INDEX
    Explanations

    terms related to client or customer, particularly in technical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <table>
    -0.39
    s
    -0.36
    decay
    -0.35
    اتها
    -0.34
     taşı
    -0.31
     Fer
    -0.31
     üzer
    -0.31
    صلاح
    -0.30
    쌓
    -0.30
     Keep
    -0.29
    POSITIVE LOGITS
     Client
    0.96
     CLIENT
    0.94
     getClient
    0.94
     Clients
    0.87
     client
    0.82
    CLIENT
    0.80
    Client
    0.80
    Clients
    0.79
    getClient
    0.78
     clientId
    0.77
    Activations Density 0.156%

    No Known Activations