© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 34-GEMMASCOPE-RES-16K
    11. 3454
    Prev
    Next
    INDEX
    Explanations

    references to semiconductor technology and fabrication processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RenderAtEndOf
    -0.48
    デフォ
    -0.38
     betweenstory
    -0.37
    yntaxException
    -0.35
    เจ
    -0.35
     libremente
    -0.35
     rotación
    -0.35
     remplacement
    -0.34
    demo
    -0.33
     χρή
    -0.33
    POSITIVE LOGITS
     robotics
    0.92
     Robotics
    0.77
     wireless
    0.74
     RFID
    0.72
     biotechnology
    0.70
     biomedical
    0.69
     microprocessor
    0.68
    Robotics
    0.68
     acoustics
    0.68
     electronics
    0.67
    Activations Density 0.950%

    No Known Activations