© 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. 3-GEMMASCOPE-RES-16K
    11. 8681
    Prev
    Next
    INDEX
    Explanations

    words related to the action of wrapping or encasing objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ponses
    -0.37
    bürger
    -0.32
    UnsafeEnabled
    -0.31
     чисто
    -0.30
    =-=-=-=-
    -0.30
    ändigen
    -0.29
    ItemId
    -0.29
    TypeInfo
    -0.29
    FirstResponder
    -0.29
     Ria
    -0.29
    POSITIVE LOGITS
     wrap
    4.25
     Wrap
    4.00
    wrap
    3.75
     wrapping
    3.67
    Wrap
    3.64
     wraps
    3.56
     wrapped
    3.39
     Wrapping
    3.36
     Wraps
    3.28
     WRAP
    3.06
    Activations Density 0.069%

    No Known Activations