© 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-2-9B
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 104341
    Prev
    Next
    INDEX
    Explanations

    descriptions of autumnal scenery and nature

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IntoConstraints
    -0.81
    httphttps
    -0.79
     propOrder
    -0.73
    ſelf
    -0.71
    MigrationBuilder
    -0.70
     ſche
    -0.66
     ſeine
    -0.66
    LookAnd
    -0.66
     resourceCulture
    -0.65
     ſch
    -0.64
    POSITIVE LOGITS
     autumn
    0.57
     Autumn
    0.54
    autumn
    0.51
    Autumn
    0.50
    🍂
    0.47
    🍁
    0.46
     fall
    0.38
     leaves
    0.38
     trees
    0.36
     leaf
    0.36
    Activations Density 0.011%

    No Known Activations