© 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-2-9B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 8543
    Prev
    Next
    INDEX
    Explanations

    complex scientific terms related to experimental systems and their behaviors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 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
     EconPapers
    -0.51
     trámite
    -0.45
     trône
    -0.44
     delegación
    -0.44
     complètes
    -0.43
     chrétien
    -0.42
     écrite
    -0.42
     supplémentaires
    -0.41
     voluntarios
    -0.41
     équipement
    -0.41
    POSITIVE LOGITS
    PreferredItem
    0.48
     behavior
    0.47
    <?>
    0.46
     experiments
    0.45
     StatefulWidget
    0.45
     चीज़ों
    0.45
    PhysRev
    0.44
     phenomena
    0.44
     experimental
    0.44
     verst
    0.44
    Activations Density 2.883%

    No Known Activations