© 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 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. 10729
    Prev
    Next
    INDEX
    Explanations

    the word "and" as a conjunction in various contexts

    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
    <%=
    -0.71
    thebibliography
    -0.68
    stdc
    -0.68
    xFFFFFF
    -0.65
    )*/
    -0.64
    amboo
    -0.61
    xffffff
    -0.61
    ^(@)
    -0.60
    Numerade
    -0.60
    منت
    -0.59
    POSITIVE LOGITS
    何より
    0.70
    And
    0.68
     Sien
    0.66
    Và
    0.65
    ppure
    0.64
     lisäksi
    0.63
    ">//
    0.61
    jména
    0.61
     daarmee
    0.61
    Και
    0.61
    Activations Density 0.257%

    No Known Activations