© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 7547
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate quantities or counts of items, particularly in reference to studies and applications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     EconPapers
    -0.47
    SourceChecksum
    -0.46
    VIAF
    -0.46
    Diwedd
    -0.42
    uxxxx
    -0.37
     âmes
    -0.35
    と思ったら
    -0.35
    Искәрмәләр
    -0.35
     STATEMENT
    -0.35
     ligiloj
    -0.34
    POSITIVE LOGITS
     many
    1.22
     numerous
    1.11
    many
    1.08
    Numerous
    1.05
     MANY
    1.05
     countless
    1.04
    MANY
    1.04
     Numerous
    1.03
     nombreuses
    0.97
     zahlreiche
    0.96
    Activations Density 0.437%

    No Known Activations