© 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. 23-GEMMASCOPE-RES-16K
    11. 11852
    Prev
    Next
    INDEX
    Explanations

    references to environmental or sustainability investments and projects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nød
    -0.85
     varandra
    -0.85
    følgelig
    -0.75
    farande
    -0.68
     jorden
    -0.67
    føring
    -0.67
     skolen
    -0.67
     måte
    -0.66
     spørs
    -0.66
     män
    -0.64
    POSITIVE LOGITS
     Swedish
    1.06
    Swedish
    0.95
     swedish
    0.93
     Sweden
    0.91
     Norwegian
    0.89
     Gothenburg
    0.87
     Bengt
    0.84
     hereof
    0.83
     Danish
    0.83
     Uppsala
    0.82
    Activations Density 0.339%

    No Known Activations