© 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. 3-GEMMASCOPE-RES-16K
    11. 7055
    Prev
    Next
    INDEX
    Explanations

    references to neurodiversity and experiences of marginalized groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     muß
    -1.08
     läßt
    -0.91
     daß
    -0.86
     mußte
    -0.80
     müßte
    -0.77
     Moslem
    -0.77
     mußten
    -0.73
     wußte
    -0.73
    faßt
    -0.72
     Schluß
    -0.67
    POSITIVE LOGITS
     incentiv
    1.23
     nuanced
    1.20
     impactful
    1.19
     relatable
    1.17
     underwhelming
    1.16
     curated
    1.14
     overarching
    1.13
     microbiome
    1.11
     tasked
    1.08
     prioritizing
    1.07
    Activations Density 4.838%

    No Known Activations