© 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. 4-GEMMASCOPE-RES-16K
    11. 11701
    Prev
    Next
    INDEX
    Explanations

    instances of the word "message" in various contexts, including errors and notifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     competir
    -0.73
    wieś
    -0.66
    curacy
    -0.66
    NegativeButton
    -0.66
     whoſe
    -0.65
    getDescriptor
    -0.65
    Atentamente
    -0.65
     Majefty
    -0.65
    γραφία
    -0.65
    farin
    -0.64
    POSITIVE LOGITS
    Message
    1.50
    getMessage
    1.25
    message
    1.13
     Message
    1.08
    MESSAGE
    0.97
     getMessage
    0.96
    essage
    0.90
    setMessage
    0.85
    MessageInfo
    0.81
     MESSAGE
    0.77
    Activations Density 0.072%

    No Known Activations