© 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. 16-GEMMASCOPE-RES-16K
    11. 16367
    Prev
    Next
    INDEX
    Explanations

    references to different layers in a system or structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "layer" or "layers"

    np_acts-logits-general · gemini-2.0-flash

    layer = or of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /**
    -0.91
     propOrder
    -0.85
    )_/¯
    -0.82
    ::_('
    -0.81
    WriteBarrier
    -0.79
     تانيه
    -0.79
    ngdoc
    -0.78
     pinulongan
    -0.78
    ethene
    -0.77
     &___
    -0.77
    POSITIVE LOGITS
     layers
    1.60
     Layers
    1.59
     Layer
    1.52
     layer
    1.50
    Layers
    1.49
     LAYER
    1.43
    layer
    1.40
    Layer
    1.38
    layers
    1.35
    LAYER
    1.24
    Activations Density 0.079%

    No Known Activations