© 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. 11-GEMMASCOPE-RES-16K
    11. 14600
    Prev
    Next
    INDEX
    Explanations

    the use of past verb forms indicating actions or events that have taken place

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cephala
    -0.69
     متعلقه
    -0.68
     démocr
    -0.67
    ardless
    -0.67
     tuff
    -0.65
     الحره
    -0.64
     actuelles
    -0.62
    atchewan
    -0.61
     pienso
    -0.59
     Familienname
    -0.59
    POSITIVE LOGITS
     earlier
    1.00
     hadn
    0.87
     hoped
    0.81
     had
    0.81
    earlier
    0.80
    Earlier
    0.77
     previously
    0.77
     Earlier
    0.74
     Había
    0.72
     previous
    0.72
    Activations Density 0.460%

    No Known Activations