© 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. 37216
    Prev
    Next
    INDEX
    Explanations

    instances of the phrase "in this" and expressions that introduce or reference specific studies or contexts

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

    this study/paper/article

    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
     للمعارف
    -0.70
    MessageTagHelper
    -0.63
    sizeCache
    -0.60
     iprot
    -0.60
     ujednoznacz
    -0.59
    setViewportView
    -0.55
    principalColumn
    -0.54
    PropertyChanging
    -0.52
     فريبيس
    -0.52
    vestream
    -0.52
    POSITIVE LOGITS
     context
    0.88
     therefore
    0.82
    Therefore
    0.81
     background
    0.81
     Therefore
    0.80
    背景
    0.80
     contexte
    0.79
     contexto
    0.79
     backdrop
    0.75
     situation
    0.72
    Activations Density 0.049%

    No Known Activations