© 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. 41-GEMMASCOPE-RES-16K
    11. 7213
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and symbols typically found in equations and proofs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ”),
    -0.70
     ],
    -0.70
    ()],
    -0.69
    "),
    -0.68
    .],
    -0.67
    ！）
    -0.66
     ])
    -0.65
    ...]
    -0.64
    。）
    -0.64
    ”).
    -0.63
    POSITIVE LOGITS
    RectangleBorder
    0.47
     NSCoder
    0.43
     مرئيه
    0.43
    الحياه
    0.39
    bootstrapcdn
    0.39
    RotationOrder
    0.39
    脚注の使い方
    0.38
    KommentareTeilen
    0.38
    buttonShape
    0.36
    PyExc
    0.35
    Activations Density 1.124%

    No Known Activations