© 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. 13044
    Prev
    Next
    INDEX
    Explanations

    terms related to statistical and mathematical concepts

    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
    
    -0.76
     متعلقه
    -0.74
    tagHelperRunner
    -0.68
    RTLR
    -0.63
    bootstrapcdn
    -0.62
    出版年
    -0.61
    ArrowToggle
    -0.59
    исленность
    -0.57
    ///</
    -0.57
     defaultstate
    -0.57
    POSITIVE LOGITS
     have
    1.80
     having
    1.70
     memiliki
    1.55
     иметь
    1.45
     mempunyai
    1.44
    having
    1.38
     имеет
    1.35
     avere
    1.34
    have
    1.33
     имеют
    1.33
    Activations Density 2.368%

    No Known Activations