© 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. 20-GEMMASCOPE-RES-16K
    11. 5350
    Prev
    Next
    INDEX
    Explanations

    technical terminology and data structures from programming and computational contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    programming code syntax and technical documentation elements.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    SequentialGroup
    -0.83
     Numerade
    -0.76
     estekak
    -0.70
    tonsoft
    -0.70
     jsPsych
    -0.69
    CloseOperation
    -0.68
     ujednoznacz
    -0.67
    पया
    -0.66
     onOptions
    -0.65
     nahilalakip
    -0.65
    POSITIVE LOGITS
     Geschä
    0.35
     Verbraucher
    0.35
     asociados
    0.34
     témoins
    0.33
     technological
    0.30
     enviados
    0.30
     bénéfices
    0.30
     technical
    0.30
     touristes
    0.30
     körper
    0.30
    Activations Density 0.231%

    No Known Activations