© 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. 31-GEMMASCOPE-RES-16K
    11. 14071
    Prev
    Next
    INDEX
    Explanations

    references to messages and message handling in programming or data processing contexts

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

    the word "Message" in technical code and documentation contexts.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/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.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    retudo
    -0.59
    CloseOperation
    -0.50
    MethodManager
    -0.47
    MergeFrom
    -0.46
     afectado
    -0.44
     humanidade
    -0.44
     afectada
    -0.43
     Stellung
    -0.42
     Wurzeln
    -0.42
    üyor
    -0.42
    POSITIVE LOGITS
     Message
    0.90
     Messages
    0.83
     message
    0.83
     msg
    0.78
     messages
    0.77
     MESSAGE
    0.77
     Msg
    0.75
     MESS
    0.73
     messaging
    0.68
    Messages
    0.67
    Activations Density 0.094%

    No Known Activations