© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 107244
    Prev
    Next
    INDEX
    Explanations

    references to various forms of online communication and support channels

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

    chat and instant messaging

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     BoxDecoration
    -0.59
    ItemBackground
    -0.54
     Ordnung
    -0.50
     HasFactory
    -0.49
    VersionUID
    -0.48
     izdel
    -0.47
     세트
    -0.47
     TRABAJO
    -0.46
    venser
    -0.46
    encanaan
    -0.46
    POSITIVE LOGITS
     chat
    0.73
     Chat
    0.62
     chats
    0.60
     chatting
    0.52
    Chat
    0.52
     CHAT
    0.51
    chat
    0.49
     Chats
    0.49
     convers
    0.46
     chatted
    0.46
    Activations Density 0.018%

    No Known Activations