© 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. 4960
    Prev
    Next
    INDEX
    Explanations

    mathematical concepts and operations related to matrices and graph theory

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

    matrix and mathematical transformations in technical text.

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

    operations that reverse, transpose, or otherwise invert direction/order or form (e.g., reversed graphs, string reversal, matrix transposes, duals/reflections).

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

    mathematical or programming operations involving matrix transposition or reversing data structures.

    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
    GEBURTSDATUM
    -0.63
    CodeAttribute
    -0.54
    ########.
    -0.51
    ftagPool
    -0.51
    +};
    -0.51
    IntoConstraints
    -0.49
    :+:
    -0.47
     myſelf
    -0.47
     &___
    -0.47
     themſelves
    -0.47
    POSITIVE LOGITS
     reversed
    0.76
     reverse
    0.74
     reverses
    0.68
     Reverse
    0.65
     reversing
    0.64
    reverse
    0.64
     revers
    0.63
     reversal
    0.63
     inverted
    0.63
    Reverse
    0.61
    Activations Density 0.593%

    No Known Activations