© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 10215
    Prev
    Next
    INDEX
    Explanations

    phrases indicating actions or changes that affect or involve multiple entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Rüyada
    -1.03
     Paglinawan
    -0.98
    GEBURTSDATUM
    -0.96
    脚注の使い方
    -0.95
    StoreMessageInfo
    -0.93
    IndentedString
    -0.87
    StructEnd
    -0.82
    addCriterion
    -0.81
     pinulongan
    -0.80
     caufe
    -0.79
    POSITIVE LOGITS
    เภ
    0.61
     ujednoznacz
    0.56
    RESH
    0.54
    elock
    0.52
     DICTION
    0.52
    Brought
    0.50
    antwo
    0.48
    ✭✭
    0.48
    कर्
    0.46
     مرت
    0.46
    Activations Density 0.439%

    No Known Activations