© 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. 12-GEMMASCOPE-RES-16K
    6. 259
    Prev
    Next
    INDEX
    Explanations

    references to specific biochemical compounds and interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mukherjee
    -0.69
    selle
    -0.69
    ستی
    -0.68
    esk
    -0.68
     Ellis
    -0.68
     Morty
    -0.67
    }));
    
    -0.66
    nelle
    -0.66
     pinulongan
    -0.65
    ılıyor
    -0.65
    POSITIVE LOGITS
     MainAxisSize
    0.96
    QApplication
    0.93
     EAP
    0.92
     Cæsar
    0.88
     tramonto
    0.85
    AccessFile
    0.84
    AnimationFrame
    0.83
     Esau
    0.82
     HasFactory
    0.81
     GAP
    0.81
    Activations Density 1.538%

    No Known Activations