© 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. 9-GEMMASCOPE-RES-131K
    11. 17314
    Prev
    Next
    INDEX
    Explanations

    phrases that express a sense of helplessness or emotional distress

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

    まま、ながら、つつ

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     spørs
    -0.41
     kysy
    -0.40
     belangrij
    -0.39
     idéia
    -0.39
     olmad
    -0.38
     šķ
    -0.38
     inconn
    -0.37
     coisa
    -0.37
     ikkje
    -0.36
     pengar
    -0.35
    POSITIVE LOGITS
    ながら
    1.69
    しながら
    1.37
     ながら
    1.18
    ながらも
    1.02
    を見ながら
    0.94
    しつつ
    0.92
    つつ
    0.90
     autorytatywna
    0.82
    
    0.75
    하며
    0.73
    Activations Density 0.005%

    No Known Activations