© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 11180
    Prev
    Next
    INDEX
    Explanations

    mathematical terms and concepts related to limits and sequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/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.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    getDoctrine
    -0.37
    Véxase
    -0.34
    Fotografía
    -0.30
     myš
    -0.29
    uertos
    -0.28
    只见
    -0.28
     Bühne
    -0.28
     custom
    -0.28
     richer
    -0.27
     ecológica
    -0.26
    POSITIVE LOGITS
    httphttps
    0.66
    Hentet
    0.64
     subsequence
    0.59
    Personendaten
    0.57
    CodedInputStream
    0.56
     ExecuteAsync
    0.55
     препратки
    0.53
    prepareStatement
    0.53
     surla
    0.53
     postIndex
    0.52
    Activations Density 1.929%

    No Known Activations