© 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-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 10295
    Prev
    Next
    INDEX
    Explanations

    elements related to chat and messaging functionalities within UI code

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

    "chat" or "Chat"

    np_acts-logits-general · gemini-2.0-flash

    chat and chatting contexts

    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
    GenerationType
    -0.81
    ArgsConstructor
    -0.69
    
    -0.63
    GIVEREF
    -0.61
     Walkover
    -0.61
    routeProvider
    -0.61
    ValueStyle
    -0.59
    HasForeignKey
    -0.57
    djangoproject
    -0.56
    mstyle
    -0.56
    POSITIVE LOGITS
     chat
    1.26
    chat
    1.24
     Chat
    1.17
    Chat
    1.11
     chats
    1.09
     Chats
    1.03
     CHAT
    1.03
    CHAT
    0.96
    Chats
    0.95
     chatting
    0.94
    Activations Density 0.151%

    No Known Activations