© 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. 11-GEMMASCOPE-RES-16K
    11. 2909
    Prev
    Next
    INDEX
    Explanations

    references to software libraries and data formats used in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    الإنجليزية
    -1.14
     Roskov
    -0.98
    ंदीखरीदारी
    -0.88
    IntoConstraints
    -0.86
    makeConstraints
    -0.77
    MemoryWarning
    -0.75
    脚注の使い方
    -0.75
    CloseOperation
    -0.74
    VersionUID
    -0.74
    writeField
    -0.73
    POSITIVE LOGITS
    millimeters
    1.49
    ContentAlignment
    0.92
    RunWith
    0.92
    HasColumnType
    0.75
     Throwable
    0.71
    ExtendWith
    0.70
    PerformLayout
    0.63
    SpringBootTest
    0.63
    queryInterface
    0.56
    Становништво
    0.51
    Activations Density 0.026%

    No Known Activations