© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 1369
    Prev
    Next
    INDEX
    Explanations

    technical specifications related to code and regions

    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
    "],
    
    -0.87
    __':
    
    -0.82
     invokingState
    -0.80
    ++)
    
    -0.79
    __':
    -0.79
    )";
    
    -0.77
    "):
    
    -0.77
    >",
    
    -0.77
    }*/
    
    -0.77
    ----</
    -0.77
    POSITIVE LOGITS
     hexadecimal
    0.74
     feroit
    0.62
    valently
    0.62
     exécu
    0.61
     arché
    0.60
     hex
    0.59
     Azer
    0.58
     ainfi
    0.58
     Freder
    0.58
     mør
    0.57
    Activations Density 0.697%

    No Known Activations