© 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. 3-GEMMASCOPE-RES-16K
    11. 9768
    Prev
    Next
    INDEX
    Explanations

    references to overnight processes or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 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
    parseFrom
    -0.78
    Xna
    -0.69
    expandindo
    -0.64
     distractions
    -0.64
     actionTypes
    -0.63
     dak
    -0.63
     Din
    -0.61
     Sas
    -0.60
     EXTR
    -0.60
     fz
    -0.59
    POSITIVE LOGITS
     overnight
    1.59
    Overnight
    1.51
     Overnight
    1.47
    vernight
    1.14
    OVERN
    0.78
    cipated
    0.75
     getItemCount
    0.74
    شهاد
    0.70
    }{*}{
    0.70
    InjectMocks
    0.69
    Activations Density 0.076%

    No Known Activations