© 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. 3-GEMMASCOPE-RES-16K
    11. 6865
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to improvement or enhancement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Es
    -0.89
    Es
    -0.79
    ArgumentParser
    -0.50
    cstdio
    -0.48
    ナビ
    -0.43
     CommandType
    -0.42
     transfieras
    -0.42
    RRect
    -0.42
    PyExc
    -0.42
    ultier
    -0.41
    POSITIVE LOGITS
     enhanced
    0.87
     enhance
    0.82
     Enhanced
    0.77
     enhancing
    0.77
    Enhanced
    0.75
     Enhance
    0.74
     es
    0.73
     enhances
    0.70
    enhance
    0.69
     Enhancing
    0.69
    Activations Density 0.030%

    No Known Activations