© 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. 41-GEMMASCOPE-RES-16K
    11. 11662
    Prev
    Next
    INDEX
    Explanations

    expressions of contemplation and personal reflection on identity and belonging

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/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.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     arrep
    -0.47
     asisten
    -0.47
     lacivert
    -0.46
     baskılı
    -0.41
     llorando
    -0.41
     parís
    -0.40
    していました
    -0.40
     ſch
    -0.40
     ſal
    -0.39
     rând
    -0.39
    POSITIVE LOGITS
     ya
    1.23
     outta
    1.18
     somethin
    1.13
     lotta
    1.09
     yer
    1.08
     nothin
    1.05
     prolly
    0.98
     gettin
    0.98
     lookin
    0.95
     ’
    0.94
    Activations Density 0.601%

    No Known Activations