© 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-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 16255
    Prev
    Next
    INDEX
    Explanations

    various types of fabricated or constructed items and their components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     táctil
    -0.36
     poivre
    -0.31
     Wilayah
    -0.30
     hendes
    -0.29
     prestations
    -0.29
     verp
    -0.28
     kommunik
    -0.28
     identité
    -0.28
     progrès
    -0.27
     bordada
    -0.27
    POSITIVE LOGITS
    DIY
    0.89
     DIY
    0.88
     homemade
    0.87
     Homemade
    0.84
    homemade
    0.82
    aarrggbb
    0.76
    Homemade
    0.76
    تقاوى
    0.75
     improvised
    0.73
     makeshift
    0.73
    Activations Density 0.247%

    No Known Activations