© 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
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 104157
    Prev
    Next
    INDEX
    Explanations

    phrases expressing the concept of being on the "wrong" path or making incorrect decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
    Ễ
    -0.34
    hbar
    -0.33
    plain
    -0.28
     verkla
    -0.28
     []*
    -0.28
    训
    -0.28
    awang
    -0.28
     const
    -0.28
    datatables
    -0.27
    となると
    -0.26
    POSITIVE LOGITS
    webElementXpaths
    0.76
    writeFieldEnd
    0.73
    Personendaten
    0.72
     wrong
    0.72
    IntoConstraints
    0.70
    MLLoader
    0.69
    TagMode
    0.68
    WRONG
    0.68
     incorrect
    0.66
     WRONG
    0.66
    Activations Density 0.076%

    No Known Activations