© 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. 10-GEMMASCOPE-RES-16K
    11. 13946
    Prev
    Next
    INDEX
    Explanations

    phrases associated with evaluations and instructions, particularly in formal contexts like legal, scientific, and procedural discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DeleteBehavior
    -0.53
    limus
    -0.46
    avadoc
    -0.42
      
    -0.42
    viewDid
    -0.41
    getClass
    -0.41
    gdala
    -0.39
    表示
    -0.39
    Hochspringen
    -0.39
    yaf
    -0.38
    POSITIVE LOGITS
     насељу
    0.84
     незавершена
    0.82
     EconPapers
    0.71
    Empereur
    0.71
    MfG
    0.71
     समीक्षक
    0.70
     برانيه
    0.70
     réguli
    0.69
     
    0.68
    NUMX
    0.68
    Activations Density 1.716%

    No Known Activations