© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 4844
    Prev
    Next
    INDEX
    Explanations

    references to chemical elements and their symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /*
    -0.88
     îna
    -0.88
    /**
    -0.83
    >*/
    -0.82
    ()");
    -0.78
     yyl
    -0.76
     inev
    -0.74
     becauſe
    -0.74
    []
    
    -0.73
     réflé
    -0.73
    POSITIVE LOGITS
     Ch
    1.29
     CH
    1.27
    Ch
    1.25
     ch
    1.24
     Chávez
    1.12
     Chom
    1.08
     Chisholm
    1.05
    CHD
    1.03
     Chuk
    1.02
    CH
    1.02
    Activations Density 0.492%

    No Known Activations