© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 9983
    Prev
    Next
    INDEX
    Explanations

    programming-related structures and definitions, particularly in the context of device drivers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    #
    -0.39
    standers
    -0.37
     kuy
    -0.36
    ?!”
    -0.35
     Catho
    -0.35
     saddles
    -0.33
    !...
    -0.32
     igång
    -0.32
     wester
    -0.32
     multiverse
    -0.32
    POSITIVE LOGITS
    ValueStyle
    1.02
    دانشنامهٔ
    0.95
    AddTagHelper
    0.95
    
    0.93
    تقاوى
    0.85
    nonatomic
    0.83
     &___
    0.82
    findpost
    0.81
    DMETHOD
    0.80
    énario
    0.78
    Activations Density 2.145%

    No Known Activations