© 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. 33-GEMMASCOPE-RES-16K
    11. 7467
    Prev
    Next
    INDEX
    Explanations

    concepts related to seasonal events and preparations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/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.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mirador
    -0.28
     löyty
    -0.28
     comedor
    -0.28
     ruok
    -0.27
    قایناقلار
    -0.26
     constaté
    -0.26
     kysy
    -0.26
    emlrt
    -0.25
    zeige
    -0.25
    szön
    -0.25
    POSITIVE LOGITS
     preparation
    3.63
     Preparation
    3.19
     preparations
    3.17
    preparation
    3.13
     prepare
    3.11
     preparing
    3.08
    Preparation
    2.94
    prepar
    2.92
     prepares
    2.91
     prepar
    2.89
    Activations Density 0.809%

    No Known Activations