© 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. 10-GEMMASCOPE-RES-16K
    11. 11072
    Prev
    Next
    INDEX
    Explanations

    terms and phrases that indicate relationships or connections between variables or entities

    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
     NSCoder
    -0.72
    Aims
    -0.64
    AxisAlignment
    -0.58
     StatelessWidget
    -0.56
    prefixer
    -0.50
    hdashline
    -0.49
    restler
    -0.48
    CodeAnalysis
    -0.48
    ссора
    -0.48
    HasAnnotation
    -0.48
    POSITIVE LOGITS
     corresponding
    1.13
    相应
    0.94
     respective
    0.93
    corresponding
    0.93
     Corresponding
    0.92
    OGND
    0.88
     counterpart
    0.87
     entsprechende
    0.86
     counterparts
    0.85
    Corresponding
    0.84
    Activations Density 0.366%

    No Known Activations