© 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-2-2B
    4. Residual Stream - 16k
    5. 7-GEMMASCOPE-RES-16K
    6. 1927
    Prev
    Next
    INDEX
    Explanations

    terms related to chat functionality and user interaction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     numberWith
    -0.96
     disambiguazione
    -0.94
     getRule
    -0.93
    /**
    -0.87
    __":
    -0.84
    redients
    -0.82
     SEDS
    -0.81
    withIdentifier
    -0.79
    __':
    
    -0.79
    UserScript
    -0.78
    POSITIVE LOGITS
     Chat
    2.07
     chat
    2.06
     CHAT
    1.88
    Chat
    1.84
    chat
    1.82
     chats
    1.61
    CHAT
    1.60
     Chats
    1.46
     Chatham
    1.46
     chatting
    1.45
    Activations Density 0.056%

    No Known Activations