© 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. 8781
    Prev
    Next
    INDEX
    Explanations

    expressions related to physical and emotional distress

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

    panic, breath, suffocation

    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
    SequentialGroup
    -0.61
    ItemBackground
    -0.57
    balleur
    -0.48
    ьажоргаш
    -0.47
    typical
    -0.44
     antics
    -0.44
    ilah
    -0.44
    anson
    -0.44
    getKeyCode
    -0.44
    Ered
    -0.44
    POSITIVE LOGITS
     claust
    0.47
    RegressionTest
    0.44
     suffoc
    0.43
     oppressive
    0.40
     respirar
    0.37
     oppressed
    0.35
    lccn
    0.35
     embreagem
    0.34
     inescapable
    0.33
     drehen
    0.33
    Activations Density 0.158%

    No Known Activations