© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 4220
    Prev
    Next
    INDEX
    Explanations

    references to public meetings and community discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     تضيفلها
    -0.88
    ########.
    -0.70
     Савезне
    -0.67
     Мексичка
    -0.64
    Diweddarwch
    -0.64
    ableness
    -0.63
    Predecesor
    -0.62
    بوابة
    -0.60
    ]='\
    -0.59
    تقاوى
    -0.59
    POSITIVE LOGITS
     tomorrow
    0.78
     Friday
    0.76
     Saturday
    0.73
     Thursday
    0.70
     will
    0.69
     Tuesday
    0.66
     Wednesday
    0.66
    Friday
    0.66
     noon
    0.65
     scheduled
    0.65
    Activations Density 0.169%

    No Known Activations