© 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-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 55222
    Prev
    Next
    INDEX
    Explanations

    references to soreness or related symptoms

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    sore, soreness, sores

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    fromUtf
    -0.49
     matrícula
    -0.45
    momix
    -0.44
     scena
    -0.44
     kons
    -0.43
     messaggio
    -0.42
    jme
    -0.42
     Kapit
    -0.41
    EndInit
    -0.41
     carcasa
    -0.41
    POSITIVE LOGITS
     sore
    2.17
    sore
    1.91
    Sore
    1.70
     Sore
    1.65
     soreness
    1.44
     sores
    1.26
     Sorensen
    0.85
    sores
    0.79
     sorely
    0.78
     bruised
    0.74
    Activations Density 0.001%

    No Known Activations