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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 12670
    Prev
    Next
    INDEX
    Explanations

    terms related to matrix properties and operations in a mathematical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IContainer
    -0.58
     kling
    -0.56
    IsContent
    -0.54
     Tit
    -0.51
     Nuit
    -0.51
     Ennis
    -0.50
    ệp
    -0.49
     Settlement
    -0.49
    amaño
    -0.48
     Galvan
    -0.48
    POSITIVE LOGITS
     matrix
    1.62
     Matrix
    1.41
     matrices
    1.38
    matrix
    1.34
    Matrix
    1.29
     matriz
    1.20
     MATRIX
    1.20
     matrice
    1.18
    矩阵
    1.17
     Matrices
    1.15
    Activations Density 1.431%

    No Known Activations