© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 7059
    Prev
    Next
    INDEX
    Explanations

    phrases related to product feedback and quality assessment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    detailed technical descriptions of model painting techniques and materials.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CYTHON
    -0.51
     pinulongan
    -0.48
    ibatis
    -0.48
    :✨
    -0.48
     nahilalakip
    -0.44
     deslig
    -0.44
    contentValues
    -0.43
    
    -0.43
     Ried
    -0.43
    Pyx
    -0.42
    POSITIVE LOGITS
     modeller
    0.87
     modell
    0.84
    模型
    0.83
     model
    0.79
     kit
    0.78
     модели
    0.75
     modelling
    0.74
     models
    0.72
     modeling
    0.72
     Modell
    0.71
    Activations Density 0.147%

    No Known Activations