© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 11971
    Prev
    Next
    INDEX
    Explanations

    terms that indicate previous positions or roles held by individuals, particularly relating to political or organizational contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 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
     ſtre
    -0.74
    httphttps
    -0.73
     pleaſure
    -0.72
    GEBURTSDATUM
    -0.71
     faſt
    -0.70
    IsContent
    -0.69
    DockStyle
    -0.69
    createStatement
    -0.66
    perature
    -0.66
     ſont
    -0.66
    POSITIVE LOGITS
     former
    1.88
     Former
    1.72
    Former
    1.71
    former
    1.54
     ehemalige
    1.34
     ehemaligen
    1.34
     mantan
    1.22
     býval
    1.19
     ehemal
    1.14
     formerly
    1.05
    Activations Density 0.179%

    No Known Activations