© 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
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 3584
    Prev
    Next
    INDEX
    Explanations

    structured data representations and mathematical expressions involving matrices

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

    mathematical notation and computational/technical terms related to matrices, dimensions, and data structures.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    mathematical notation related to matrices, dimensions, and arrays.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    mentions of matrices and arrays, especially references to their dimensions, entries/elements, and matrix-related notation or operations.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    mathematical notation describing matrices, their dimensions, and their elements.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 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
     getItemCount
    -0.75
    HomeAsUpEnabled
    -0.59
     Shakspeare
    -0.59
     wherefore
    -0.57
    RegistryLite
    -0.56
     الرياضيه
    -0.55
     TestBed
    -0.54
    dafx
    -0.54
    UrlResolution
    -0.53
    AxisAlignment
    -0.53
    POSITIVE LOGITS
     matrix
    0.56
    Matrix
    0.51
    matrix
    0.49
     матри
    0.48
     Matrix
    0.47
     matrices
    0.47
     MATRIX
    0.40
    矩阵
    0.40
    Matriz
    0.39
    MATRIX
    0.38
    Activations Density 0.514%

    No Known Activations