© 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. 16-GEMMASCOPE-RES-16K
    11. 8206
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and their placements in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Comes after a period

    np_acts-logits-general · gemini-2.0-flash

    demonstratives in various languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للمعارف
    -0.99
    Geplaatst
    -0.93
     AssemblyCulture
    -0.89
    AllAfrica
    -0.85
    WriteTagHelper
    -0.84
    extAlignment
    -0.84
     disambiguazione
    -0.82
    RTLD
    -0.80
     fieldNum
    -0.80
    UnknownFields
    -0.80
    POSITIVE LOGITS
     acesta
    0.51
    сюда
    0.43
     «
    0.42
    ↵
    0.42
     auxquels
    0.41
     After
    0.40
    After
    0.39
     căr
    0.39
     acestea
    0.39
     after
    0.39
    Activations Density 0.197%

    No Known Activations