© 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. 30-GEMMASCOPE-RES-16K
    11. 15415
    Prev
    Next
    INDEX
    Explanations

    instances of emotional or social impact related to personal experiences and societal norms

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

    preceding subjective feelings or judgments

    np_acts-logits-general · gemini-2.0-flash

    intrigued by or striking

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     StatelessWidget
    -0.48
     StatefulWidget
    -0.45
    Aiheesta
    -0.43
    InputBorder
    -0.42
    EMBER
    -0.42
     Wiktionnaire
    -0.41
     AssemblyTitle
    -0.40
     doInBackground
    -0.40
    MessageTagHelper
    -0.40
    MemoryWarning
    -0.40
    POSITIVE LOGITS
     fascin
    1.04
     annoys
    0.98
     intrigued
    0.91
     scares
    0.91
     excites
    0.90
     amaze
    0.88
     impressed
    0.87
     fascinated
    0.86
     intrigues
    0.80
     strikes
    0.77
    Activations Density 0.459%

    No Known Activations