© 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. 10409
    Prev
    Next
    INDEX
    Explanations

    phrases that express uncertainty or possibility

    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
    ollectionView
    -0.91
     énergé
    -0.84
    runApp
    -0.78
    Composable
    -0.78
     Comer
    -0.77
     Renner
    -0.74
     TextAppearance
    -0.73
    interopRequire
    -0.72
    AutoScaleMode
    -0.71
    GEBURTSDATUM
    -0.69
    POSITIVE LOGITS
     might
    1.65
     MIGHT
    1.52
     Might
    1.50
    might
    1.42
    Might
    1.35
     may
    1.28
     could
    1.12
     MAY
    1.12
     would
    1.03
     not
    1.00
    Activations Density 0.029%

    No Known Activations