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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 5178
    Prev
    Next
    INDEX
    Explanations

    legal terminology and concepts related to compensation and employment law

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     microbiome
    -1.20
     impactful
    -1.12
     onboarding
    -1.08
    TLDR
    -1.07
     curated
    -1.06
     incentiv
    -1.03
     LGBTQ
    -1.00
     immersive
    -0.97
     nuanced
    -0.96
     
    -0.96
    POSITIVE LOGITS
     muß
    1.41
     läßt
    1.41
     daß
    1.38
     idéia
    1.31
     müßte
    1.25
     Moslem
    1.19
     Daß
    1.13
     mußte
    1.12
     mußten
    1.08
     skall
    1.03
    Activations Density 8.643%

    No Known Activations