© 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 - 65k
    9. 0-GEMMASCOPE-RES-65K
    11. 9182
    Prev
    Next
    INDEX
    Explanations

    references to the national context or issues related to national identity or policy

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    WireFormatLite
    -0.57
     createSprite
    -0.56
     Betracht
    -0.53
     myſelf
    -0.53
     []:
    -0.52
     stof
    -0.51
     tối
    -0.50
     Pues
    -0.49
    xaml
    -0.48
     Virg
    -0.47
    POSITIVE LOGITS
     national
    1.59
     National
    1.51
    National
    1.46
    national
    1.43
     nacional
    1.26
     NATIONAL
    1.20
     nationale
    1.16
     nazionale
    1.13
    NATIONAL
    1.13
     nasional
    0.98
    Activations Density 0.082%

    No Known Activations