© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 52898
    Prev
    Next
    INDEX
    Explanations

    keywords and phrases related to legal or judicial contexts

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

    incoherent, irrational, or delusional speech

    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
     encima
    -0.36
    Kontra
    -0.36
    switch
    -0.34
     Вікі
    -0.32
     ederim
    -0.31
     >=",
    -0.31
     contraire
    -0.30
     Archiproducts
    -0.30
    ズル
    -0.30
    endrait
    -0.30
    POSITIVE LOGITS
     betweenstory
    0.68
     incoherent
    0.60
     lunatic
    0.59
     delusional
    0.58
     crazy
    0.55
     madness
    0.55
     irrational
    0.54
    coher
    0.54
     folle
    0.54
    疯
    0.54
    Activations Density 0.080%

    No Known Activations