© 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. 34-GEMMASCOPE-RES-16K
    11. 6997
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to data or material processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     geçti
    -0.38
     ki
    -0.37
     thạch
    -0.35
     تعدى
    -0.35
     بيها
    -0.34
    tagHelperRunner
    -0.34
     Aussch
    -0.32
     çı
    -0.32
     bulundu
    -0.32
     Z
    -0.31
    POSITIVE LOGITS
    ization
    1.77
    ized
    1.74
    izing
    1.70
    ize
    1.63
    化
    1.55
    izations
    1.52
    isation
    1.52
    izes
    1.51
    izers
    1.49
    IZATION
    1.48
    Activations Density 0.720%

    No Known Activations