© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 104509
    Prev
    Next
    INDEX
    Explanations

    topics related to education and academic disciplines

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    AddTagHelper
    -0.80
    exels
    -0.64
    itattu
    -0.61
     nahilalakip
    -0.57
    +#+#
    -0.56
    featureID
    -0.55
    SBATCH
    -0.55
    TagMode
    -0.54
    enderror
    -0.52
     يتيمه
    -0.52
    POSITIVE LOGITS
     courseId
    0.41
     teach
    0.37
    Népesség
    0.36
     vocales
    0.36
     taught
    0.36
     defaultstate
    0.34
     teaching
    0.34
    ensiva
    0.33
     citoy
    0.32
     courses
    0.31
    Activations Density 0.008%

    No Known Activations