© 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-2-2B
    7. Residual Stream - 16k
    9. 6-GEMMASCOPE-RES-16K
    11. 5784
    Prev
    Next
    INDEX
    Explanations

    instances of the word "retrieve" and its variations related to data retrieval processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Folsom
    -0.76
     Mahomet
    -0.76
     aggiunge
    -0.73
     fotográfico
    -0.72
     newState
    -0.71
    pardon
    -0.70
     hjel
    -0.70
     Pardon
    -0.70
     Yoh
    -0.69
     Charlemagne
    -0.69
    POSITIVE LOGITS
     retrieved
    1.36
     retrieve
    1.33
    Retrieved
    1.23
     Retrieval
    1.21
    Retrieve
    1.20
     Retrieve
    1.19
     retrieves
    1.15
    rieved
    1.15
     retrieving
    1.14
    Retrieval
    1.11
    Activations Density 0.065%

    No Known Activations