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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 8669
    Prev
    Next
    INDEX
    Explanations

    references to utility functions and math-related classes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Contribution
    -0.53
     professionali
    -0.51
    EXPECT
    -0.50
     poved
    -0.50
     pet
    -0.48
     Contribution
    -0.48
     berpeng
    -0.48
     professionale
    -0.47
    弊
    -0.47
     gerek
    -0.46
    POSITIVE LOGITS
     المعيارى
    0.77
    yntaxException
    0.74
     سكانية
    0.72
     الحره
    0.71
     CURIAM
    0.70
    WireFormatLite
    0.68
    hyrchwyd
    0.65
     FetchType
    0.64
    脚注の使い方
    0.62
    WireFormat
    0.58
    Activations Density 0.019%

    No Known Activations