© 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. 5178
    Prev
    Next
    INDEX
    Explanations

    references to a specific cultural or geographic identity, particularly that associated with the Pacific

    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
    ErrUnexpectedEOF
    -0.62
    WebElementEntity
    -0.54
    Viitteet
    -0.53
     jurídica
    -0.52
     noDo
    -0.51
     zewnętrzne
    -0.51
     CallOverrides
    -0.51
    TargetException
    -0.50
    Искәрмәләр
    -0.50
    RefNanny
    -0.49
    POSITIVE LOGITS
    sives
    0.57
    sivity
    0.56
    siveness
    0.55
    mergeFrom
    0.54
    sista
    0.51
    siv
    0.51
    ENCOD
    0.49
     Ocho
    0.48
    sto
    0.48
     rappelle
    0.47
    Activations Density 0.253%

    No Known Activations