© 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 EvalsExportsAPI 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. 11262
    Prev
    Next
    INDEX
    Explanations

    references to different levels or layers of complexity or hierarchy

    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
     utafitiHapana
    -0.72
     AssemblyProduct
    -0.70
    RenderAtEndOf
    -0.67
    لينكات
    -0.54
    ResponseWriter
    -0.52
     vre
    -0.51
    urlpatterns
    -0.51
    ربة
    -0.51
    ंदीखरीदारी
    -0.51
     recevez
    -0.50
    POSITIVE LOGITS
     level
    1.52
     LEVEL
    1.33
    level
    1.29
     levels
    1.28
     Level
    1.28
    LEVEL
    1.28
    Level
    1.20
     Levels
    1.02
    levels
    1.01
     LEVELS
    0.98
    Activations Density 0.447%

    No Known Activations