© 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. 20-GEMMASCOPE-RES-131K
    11. 89697
    Prev
    Next
    INDEX
    Explanations

    instances of the word "generous" and its variations in the context of giving or providing support

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

    generous support or gifts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Iraq
    -0.43
     Polri
    -0.42
     Ishi
    -0.41
     what
    -0.39
     russes
    -0.39
     quoi
    -0.38
    qxd
    -0.38
     Rússia
    -0.37
     Polda
    -0.36
     ça
    -0.36
    POSITIVE LOGITS
     generous
    1.13
     Generous
    1.12
     generosity
    0.96
     generously
    0.90
     großzü
    0.69
    olesome
    0.65
     Bioaccumulative
    0.64
     genero
    0.63
     فريبيس
    0.63
    itarian
    0.63
    Activations Density 0.006%

    No Known Activations