© 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. 2-GEMMASCOPE-RES-16K
    11. 2060
    Prev
    Next
    INDEX
    Explanations

    the verb "to be" in its various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyCulture
    -0.73
    Lähteet
    -0.73
     myſelf
    -0.69
     ourselves
    -0.68
    archiviato
    -0.67
    Chúng
    -0.65
    RectangleBorder
    -0.65
     itſelf
    -0.65
    áctenos
    -0.64
    themselves
    -0.63
    POSITIVE LOGITS
     your
    1.04
     Your
    1.03
    Your
    0.95
    your
    0.93
     YOUR
    0.83
    YOUR
    0.78
     votre
    0.77
     You
    0.76
     youre
    0.73
     you
    0.70
    Activations Density 0.086%

    No Known Activations