© 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. 2-GEMMASCOPE-RES-16K
    11. 4175
    Prev
    Next
    INDEX
    Explanations

    references to tours or guided experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     honor
    -0.64
     HONOR
    -0.64
     Honor
    -0.63
    Życiorys
    -0.60
    Honor
    -0.60
    isement
    -0.60
    upp
    -0.57
     Dish
    -0.56
    PendingIntent
    -0.54
    сти
    -0.54
    POSITIVE LOGITS
     tour
    2.73
     tours
    2.64
     Tour
    2.47
    tour
    2.40
    Tour
    2.40
     TOUR
    2.36
     Tours
    2.20
    tours
    2.06
     toured
    2.05
    Tours
    2.03
    Activations Density 0.083%

    No Known Activations