© 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-2-9B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 13910
    Prev
    Next
    INDEX
    Explanations

    references to collaborative and social activities, often involving local community organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 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
     Orgel
    -0.64
     Zwiebel
    -0.63
     Nieren
    -0.57
     Leinwand
    -0.56
     Bienen
    -0.56
     Feier
    -0.56
     Erde
    -0.54
     Glied
    -0.54
     Stirn
    -0.54
     Todes
    -0.54
    POSITIVE LOGITS
    rungsseite
    0.92
    Transkript
    0.81
     Photocase
    0.80
     الحره
    0.80
    Personensuche
    0.80
    Hochspringen
    0.78
    OGND
    0.77
    GEBURTSDATUM
    0.75
    Einzelnachweise
    0.69
    Aholisi
    0.64
    Activations Density 6.308%

    No Known Activations