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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 8030
    Prev
    Next
    INDEX
    Explanations

    references to "client" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ]]=
    -0.31
     Ordnung
    -0.30
     dotyczące
    -0.30
    ]=="
    -0.30
     {?}
    -0.28
     the
    -0.28
     gerichtet
    -0.28
     How
    -0.27
     seguía
    -0.27
    之下
    -0.27
    POSITIVE LOGITS
     client
    3.45
     Client
    3.28
    Client
    3.28
    client
    3.05
     Clients
    2.89
     clients
    2.88
     CLIENT
    2.84
    CLIENT
    2.69
    Clients
    2.61
    clients
    2.50
    Activations Density 0.101%

    No Known Activations