© 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
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 2944
    Prev
    Next
    INDEX
    Explanations

    keywords related to production and development processes

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

    the word "development" in various contexts.

    oai_token-act-pair · claude-4-5-haiku
    Triggered 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
    Negative Logits
     mempel
    -0.47
     Arten
    -0.32
     lâmpada
    -0.32
     Arque
    -0.32
     daire
    -0.32
    wość
    -0.32
     TÉCNICA
    -0.31
     embreagem
    -0.31
     pengantin
    -0.31
    rboles
    -0.30
    POSITIVE LOGITS
    zzleHttp
    0.81
    onViewCreated
    0.75
     CreateTagHelper
    0.73
    windowFixed
    0.69
     nahilalakip
    0.67
    aarrggbb
    0.66
    
    0.65
     EconPapers
    0.65
     queſta
    0.65
    OGND
    0.64
    Activations Density 0.601%

    No Known Activations