© 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. 16-GEMMASCOPE-RES-16K
    11. 5873
    Prev
    Next
    INDEX
    Explanations

    references to messages and communication systems

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

    "message" or a close variation

    np_acts-logits-general · gemini-2.0-flash

    message

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IBinder
    -0.79
     connus
    -0.76
     sauvages
    -0.69
     actuels
    -0.66
    دانشنامهٔ
    -0.65
     venons
    -0.64
     moletom
    -0.64
     conocía
    -0.64
     abandonné
    -0.63
     domestiques
    -0.62
    POSITIVE LOGITS
     messages
    1.58
     Messages
    1.38
     message
    1.37
    messages
    1.34
     Message
    1.27
    Messages
    1.22
    getMessage
    1.14
     getMessage
    1.11
     MESSAGE
    1.09
     mes
    1.09
    Activations Density 0.153%

    No Known Activations