© 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. 24936
    Prev
    Next
    INDEX
    Explanations

    expressions related to concerns and conditions of interpersonal relationships

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

    occasional or slightly

    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
    endale
    -0.42
     chyba
    -0.35
    iae
    -0.35
    writel
    -0.33
    انظر
    -0.33
     niestety
    -0.33
     fä
    -0.33
     feasibility
    -0.32
    foreach
    -0.32
     available
    -0.32
    POSITIVE LOGITS
     occasional
    0.94
     occasionally
    0.86
    Slightly
    0.81
     slightly
    0.80
    slightly
    0.77
     Slightly
    0.75
    Occasionally
    0.73
    偶尔
    0.71
     Occasional
    0.70
     geleg
    0.70
    Activations Density 0.065%

    No Known Activations