© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 4113
    Prev
    Next
    INDEX
    Explanations

    basic prepositions and conjunctions in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/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.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     camada
    -0.41
    omyces
    -0.39
     memb
    -0.38
    Eins
    -0.38
    -
    -0.38
     liên
    -0.38
    ‌
    -0.38
     First
    -0.37
     gleichzeitig
    -0.37
    icial
    -0.36
    POSITIVE LOGITS
     kasarigan
    1.26
    GEBURTSDATUM
    1.06
    Datuak
    1.05
    Portale
    1.05
    InjectAttribute
    1.03
     تضيفلها
    1.03
    IndentedString
    1.01
    andExpect
    0.99
    Personensuche
    0.97
     ویکی‌پدیای
    0.96
    Activations Density 1.102%

    No Known Activations