© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 12307
    Prev
    Next
    INDEX
    Explanations

    technical terms related to electronics and time synchronization

    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
     autorytatywna
    -0.47
     насељу
    -0.46
    WebElementEntity
    -0.42
    tanleria
    -0.41
    sellor
    -0.36
    timacy
    -0.35
    SourceChecksum
    -0.35
    awtextra
    -0.35
     IgA
    -0.34
     gắng
    -0.34
    POSITIVE LOGITS
     clock
    1.98
     clocks
    1.71
     Clock
    1.71
    clock
    1.63
    Clock
    1.58
     CLOCK
    1.57
     Clocks
    1.53
     reloj
    1.41
    CLOCK
    1.35
     ticking
    1.28
    Activations Density 0.715%

    No Known Activations