© 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-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 1379
    Prev
    Next
    INDEX
    Explanations

    programming-related constructs and message handling in code

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

    Code or configuration related to "message"

    np_acts-logits-general · gemini-2.0-flash

    messages or msg

    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
    DockStyle
    -0.67
    complexContent
    -0.66
    LookAnd
    -0.64
    بوابة
    -0.63
    CopyWith
    -0.63
    aarrggbb
    -0.62
    存于互联网档案馆
    -0.60
    ChildScrollView
    -0.60
     utafitiHapana
    -0.58
     externi
    -0.57
    POSITIVE LOGITS
     message
    2.87
     Message
    2.60
    message
    2.57
    Message
    2.52
     messages
    2.47
     MESSAGE
    2.35
     msg
    2.31
    msg
    2.19
    MESSAGE
    2.15
     Messages
    2.15
    Activations Density 0.121%

    No Known Activations