© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 7980
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "chat"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     endblock
    -0.35
     Israelis
    -0.35
    endcsname
    -0.35
     Mn
    -0.34
    dataIndex
    -0.34
    cionais
    -0.34
     Rosa
    -0.33
     Balt
    -0.33
    ifndef
    -0.33
    iant
    -0.32
    POSITIVE LOGITS
     chat
    4.25
     Chat
    3.80
    Chat
    3.69
    chat
    3.63
     CHAT
    3.34
    CHAT
    3.02
     chats
    3.02
     chatting
    2.78
     chatted
    2.69
    chats
    2.55
    Activations Density 0.075%

    No Known Activations