© 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. 21-GEMMASCOPE-RES-16K
    11. 9230
    Prev
    Next
    INDEX
    Explanations

    actions involving the concept of wrapping or enclosing something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/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.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RegistryLite
    -0.81
    MLLoader
    -0.69
     transférez
    -0.65
     utafitiHapana
    -0.62
     Bluff
    -0.60
    zeera
    -0.59
     Roskov
    -0.59
     Alegre
    -0.58
     يتيمه
    -0.57
    Kanpo
    -0.57
    POSITIVE LOGITS
     wrap
    1.61
     wrapped
    1.51
     wraps
    1.51
     wrapping
    1.45
     Wrap
    1.44
     Wrapping
    1.35
     around
    1.32
    Wrap
    1.31
    wrap
    1.30
    Wrapping
    1.29
    Activations Density 0.131%

    No Known Activations