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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 9599
    Prev
    Next
    INDEX
    Explanations

    references to a specific individual named Su

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Región
    -0.46
     Infórmanos
    -0.44
    ंदीखरीदारी
    -0.43
    깥
    -0.42
     Segurança
    -0.39
    RowCount
    -0.38
     pregunto
    -0.37
    WillAppear
    -0.37
    GEBURTSDATUM
    -0.36
     demais
    -0.35
    POSITIVE LOGITS
     platform
    0.86
     ticket
    0.72
     tickets
    0.72
     Ticket
    0.72
     Tickets
    0.68
    platform
    0.68
     deal
    0.65
     button
    0.64
    Ticket
    0.62
    Tickets
    0.61
    Activations Density 0.217%

    No Known Activations