© 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. 102469
    Prev
    Next
    INDEX
    Explanations

    file paths or URLs related to resource loading

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

    directory path components

    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
     виправивши
    -0.70
     utafitiHapana
    -0.65
    PerformLayout
    -0.65
    Hentet
    -0.56
    sizeCache
    -0.55
    AutoField
    -0.54
     resourceCulture
    -0.52
     createState
    -0.52
    ThroughAttribute
    -0.52
     enfans
    -0.51
    POSITIVE LOGITS
    ../../../
    1.69
    ../../
    1.44
     '../../../../
    0.98
     "../../../../
    0.92
    ="../../
    0.88
     ../../
    0.84
    ('../../../
    0.82
     '../../
    0.79
     "../../
    0.77
    ..\..\
    0.70
    Activations Density 0.004%

    No Known Activations