© 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. 25-GEMMASCOPE-RES-16K
    11. 2471
    Prev
    Next
    INDEX
    Explanations

    references to specific events, actions, or statistical data in legal or educational contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     clothing
    -1.37
     clothes
    -1.32
     Clothing
    -1.25
    Clothing
    -1.23
     Clothes
    -1.22
     garments
    -1.20
     CLOTH
    -1.19
     garment
    -1.17
     dress
    -1.16
     apparel
    -1.14
    POSITIVE LOGITS
    Juego
    0.45
    ूस
    0.44
    砲
    0.44
    wine
    0.44
    setzer
    0.42
     Oral
    0.42
     wheat
    0.41
     oral
    0.40
     torte
    0.39
     Drinks
    0.39
    Activations Density 1.305%

    No Known Activations