© 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. 3036
    Prev
    Next
    INDEX
    Explanations

    statistical data related to housing and living conditions

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

    statistical data and comparative numerical information presented in structured formats.

    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
    ValueStyle
    -0.79
     Савезне
    -0.75
     beginnetje
    -0.73
    queryInterface
    -0.68
    HideFlags
    -0.62
     Meksiku
    -0.60
     wireType
    -0.59
     Venez
    -0.59
    DotNetBar
    -0.58
     HttpNotFound
    -0.58
    POSITIVE LOGITS
     costes
    0.64
     vuestro
    0.59
     vuestros
    0.56
     vuestra
    0.52
     podéis
    0.52
     nº
    0.51
     imprescindible
    0.50
     acabó
    0.49
     Zweifel
    0.48
     vosotros
    0.48
    Activations Density 0.149%

    No Known Activations