© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 6665
    Prev
    Next
    INDEX
    Explanations

    thematic elements related to youth and satire in media

    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
     incentiv
    -1.07
     nuanced
    -1.02
     relatable
    -1.02
     underwhelming
    -1.02
     impactful
    -1.00
     overarching
    -0.99
     entirety
    -0.98
     prioriti
    -0.98
     curated
    -0.97
     tasked
    -0.94
    POSITIVE LOGITS
     muß
    1.16
     läßt
    1.02
     daß
    0.98
     Moslem
    0.92
     müßte
    0.91
     mußte
    0.90
    faßt
    0.85
     mußten
    0.85
     wußte
    0.84
     biß
    0.78
    Activations Density 4.551%

    No Known Activations