© 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. 25-GEMMASCOPE-RES-16K
    11. 8478
    Prev
    Next
    INDEX
    Explanations

    technical terms related to mechanical engineering and sealing systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kasarigan
    -0.68
    Hozzáférés
    -0.60
    WebServlet
    -0.56
     Waray
    -0.56
     мәкал
    -0.55
    цездатний
    -0.54
     ThemeData
    -0.52
    Джерела
    -0.52
     nahilalakip
    -0.51
    ंदीखरीदारी
    -0.51
    POSITIVE LOGITS
     seal
    1.16
     sealing
    1.10
     sealant
    1.08
     seals
    1.04
    seal
    0.99
     Seal
    0.98
    Seal
    0.97
     Sealing
    0.95
     sealer
    0.87
     caul
    0.85
    Activations Density 0.588%

    No Known Activations