© 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-2-2B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 2741
    Prev
    Next
    INDEX
    Explanations

    terms and expressions related to mathematical notation and equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     transparence
    -0.55
     sencillas
    -0.51
    cepción
    -0.51
     lanterna
    -0.49
     enamorado
    -0.49
     argint
    -0.49
     hjelp
    -0.48
     ouverts
    -0.48
     zví
    -0.47
     singkat
    -0.47
    POSITIVE LOGITS
    MessageTagHelper
    0.78
     يتيمه
    0.75
    TagMode
    0.73
    /**
    0.68
    Geplaatst
    0.67
    consulté
    0.64
    apunov
    0.64
     ControllerBase
    0.64
    didSet
    0.63
     pstmt
    0.63
    Activations Density 1.854%

    No Known Activations