© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 12-GEMMASCOPE-RES-16K
    11. 2378
    Prev
    Next
    INDEX
    Explanations

    references to layers in a multi-layer context, particularly in relation to thickness and properties

    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
     maș
    -0.89
     MHD
    -0.86
    )_/¯
    -0.83
    ]--;
    -0.82
    /**
    -0.78
     riconoscimento
    -0.76
    DotNetBar
    -0.75
    ethene
    -0.75
     commercio
    -0.74
     weevil
    -0.74
    POSITIVE LOGITS
     layers
    1.77
     Layers
    1.76
     Layer
    1.75
     layer
    1.73
    Layers
    1.60
    layer
    1.60
    Layer
    1.59
     LAYER
    1.57
    layers
    1.48
    LAYER
    1.42
    Activations Density 0.062%

    No Known Activations