© 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. 20-GEMMASCOPE-RES-131K
    11. 116799
    Prev
    Next
    INDEX
    Explanations

    terms related to copyright and registration processes

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     Infór
    -0.64
    pecabe
    -0.63
     integridad
    -0.60
    NameInMap
    -0.60
    principalColumn
    -0.58
     démocr
    -0.57
     Monfieur
    -0.57
     civilización
    -0.56
     desmotivaciones
    -0.56
    ſelves
    -0.56
    POSITIVE LOGITS
     reserving
    0.48
     claim
    0.46
     reserve
    0.43
     reservation
    0.43
    Портал
    0.42
     puja
    0.41
     reserved
    0.40
    占
    0.40
     pers
    0.40
    anh
    0.40
    Activations Density 0.045%

    No Known Activations