© 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. 20-GEMMASCOPE-RES-16K
    11. 72
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and notations related to matrices and linear algebra

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

    matrices and matrix operations

    np_acts-logits-general · gemini-2.0-flash

    diagonal, symmetric, or singular matrix

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    ंदीखरीदारी
    -0.56
    SourceChecksum
    -0.53
    amaño
    -0.52
    ellees
    -0.52
     camicia
    -0.51
    Kaynakça
    -0.50
    xtext
    -0.49
    campe
    -0.49
    atellite
    -0.49
    จบ
    -0.48
    POSITIVE LOGITS
     matrix
    1.48
     Matrix
    1.32
     matrices
    1.28
    matrix
    1.21
    Matrix
    1.21
     matrice
    1.13
     MATRIX
    1.13
    矩阵
    1.11
     matriz
    1.10
    MATRIX
    1.07
    Activations Density 1.502%

    No Known Activations