© 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 - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 931
    Prev
    Next
    INDEX
    Explanations

    phrases related to introductory or contextual elements in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pleaſure
    -0.71
     purpoſe
    -0.71
     ſta
    -0.70
     himſelf
    -0.70
     uſed
    -0.69
     Theſe
    -0.69
     myſelf
    -0.68
     itſelf
    -0.67
    ähteet
    -0.66
     raiſ
    -0.65
    POSITIVE LOGITS
     in
    1.12
     In
    0.95
    In
    0.74
     within
    0.73
     IN
    0.73
     وفي
    0.70
     dans
    0.69
    InThe
    0.66
     trong
    0.65
     midst
    0.65
    Activations Density 0.492%

    No Known Activations