© 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. 23-GEMMASCOPE-RES-16K
    11. 5336
    Prev
    Next
    INDEX
    Explanations

    descriptions of vehicles and their features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     créativité
    -0.58
     compréhen
    -0.56
    Filmografia
    -0.54
     fréquence
    -0.54
     دیکھیے
    -0.53
    apimachinery
    -0.53
    Personendaten
    -0.53
    évaluateur
    -0.53
    öffnet
    -0.51
     panoramique
    -0.51
    POSITIVE LOGITS
     handling
    0.73
     nimble
    0.71
     agile
    0.65
     MainAxisSize
    0.63
     Teut
    0.63
     Handling
    0.63
     performance
    0.63
    handling
    0.61
     refinement
    0.61
    HANDLING
    0.60
    Activations Density 0.148%

    No Known Activations