© 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. 15-GEMMASCOPE-RES-16K
    11. 2990
    Prev
    Next
    INDEX
    Explanations

    terms related to Borel transformations and their properties in mathematical analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Arnold
    -0.59
     ARNOLD
    -0.57
    Arnold
    -0.49
     civiliz
    -0.49
     Lawler
    -0.49
     Cardio
    -0.48
     第三
    -0.48
     Alp
    -0.48
    providedIn
    -0.47
     AUSTR
    -0.47
    POSITIVE LOGITS
    eux
    0.54
    Carey
    0.52
    Caleb
    0.51
    jenigen
    0.50
     ſich
    0.49
     varandra
    0.49
    USET
    0.48
    kei
    0.48
     varones
    0.47
    pcm
    0.47
    Activations Density 1.906%

    No Known Activations