© 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. 5-GEMMASCOPE-RES-16K
    11. 9246
    Prev
    Next
    INDEX
    Explanations

    transitional phrases and indicators of progression in a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GEBURTSDATUM
    -1.26
    ImageContext
    -0.94
    SharedDtor
    -0.93
    ConstraintMaker
    -0.89
    MessageOf
    -0.86
    oredCriteria
    -0.84
     Италијани
    -0.83
     Italijani
    -0.81
     мәкал
    -0.80
    Datuak
    -0.77
    POSITIVE LOGITS
    CloseOperation
    0.42
    restes
    0.41
    Preconditions
    0.40
     estimés
    0.40
     dikatakan
    0.40
     recensement
    0.40
    ayak
    0.38
    Ссылки
    0.37
     federal
    0.37
    Formik
    0.37
    Activations Density 0.366%

    No Known Activations