© 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. 84268
    Prev
    Next
    INDEX
    Explanations

    references to specific actions, qualities, or descriptions related to surroundings and settings

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

    Russian greetings and goodbyes

    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
    AsUp
    -0.70
     defaultstate
    -0.67
    ſelf
    -0.65
     purpoſe
    -0.62
    脚注の使い方
    -0.60
     myſelf
    -0.60
    tanleria
    -0.60
     pleaſure
    -0.60
    astéroïdes
    -0.59
    VYMaps
    -0.57
    POSITIVE LOGITS
     rând
    0.39
     acoper
    0.34
    "]();
    0.31
     noastră
    0.31
     bordados
    0.30
     telinga
    0.29
    ")))
    0.29
     يتيمه
    0.28
    getColumnIndex
    0.28
     riscal
    0.27
    Activations Density 0.004%

    No Known Activations