© 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. 2927
    Prev
    Next
    INDEX
    Explanations

    preferences and choices related to various topics

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

    phrases expressing preference or recommendation between options.

    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
    //
    -0.28
    umpang
    -0.27
     merak
    -0.26
    บล
    -0.24
     делу
    -0.24
     Italijanski
    -0.22
    hilangan
    -0.21
    žnost
    -0.21
    chluss
    -0.20
     Sorg
    -0.20
    POSITIVE LOGITS
     preference
    3.31
     prefer
    3.20
     preferred
    3.08
     Preference
    2.94
     prefers
    2.92
    prefer
    2.92
     Prefer
    2.91
     preferring
    2.86
    preference
    2.80
    preferred
    2.73
    Activations Density 0.684%

    No Known Activations