© 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. 27867
    Prev
    Next
    INDEX
    Explanations

    phrases related to descriptions and details

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

    description or describing

    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
    principalColumn
    -0.77
    jsonwebtoken
    -0.66
     ſind
    -0.66
    GEBURTSDATUM
    -0.66
     AssemblyCulture
    -0.65
    
    -0.62
    edicated
    -0.62
     ſein
    -0.61
    TargetException
    -0.59
    olidated
    -0.59
    POSITIVE LOGITS
     description
    1.54
     descriptions
    1.37
    description
    1.21
     Description
    1.19
     describing
    1.17
     describe
    1.16
    Description
    1.13
     DESCRIPTION
    1.10
     descripción
    1.08
     describes
    1.06
    Activations Density 0.058%

    No Known Activations