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

    Neuronpedia

    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-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 111687
    Prev
    Next
    INDEX
    Explanations

    mentions of various groups of people, particularly students and researchers

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

    groups and their actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     itſelf
    -0.61
     ſta
    -0.60
     Monfieur
    -0.59
    хьтан
    -0.59
     fusca
    -0.59
    ſelves
    -0.53
     ſol
    -0.53
    ⤹
    -0.52
     verſ
    -0.50
     dAtA
    -0.50
    POSITIVE LOGITS
     everywhere
    0.50
    们
    0.47
     fleste
    0.44
     mulighed
    0.43
     רבים
    0.42
    들의
    0.38
     themselves
    0.38
     vrea
    0.36
     زیادی
    0.36
     can
    0.35
    Activations Density 0.125%

    No Known Activations