© 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. 9-GEMMASCOPE-RES-16K
    11. 1724
    Prev
    Next
    INDEX
    Explanations

    various closing braces and delimiters in a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ?>">
    -0.99
     Teb
    -0.92
     PDS
    -0.84
     Andree
    -0.84
    criminator
    -0.80
     Duch
    -0.78
     oeufs
    -0.78
     Ceres
    -0.77
     Ruck
    -0.77
     Theron
    -0.76
    POSITIVE LOGITS
     }
    1.05
    PerformLayout
    0.89
     MonoBehaviour
    0.84
     Bucky
    0.75
    osex
    0.74
    ••••
    0.73
    PMailer
    0.73
     
    0.72
     Phuket
    0.71
     Colby
    0.71
    Activations Density 0.137%

    No Known Activations