© 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. 11-GEMMASCOPE-RES-16K
    11. 10504
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "can" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PerformLayout
    -0.94
    GEBURTSDATUM
    -0.83
     azzurro
    -0.76
    Lähteet
    -0.75
    tieth
    -0.74
     Affiliations
    -0.74
     layui
    -0.74
    EDEFAULT
    -0.73
     postres
    -0.69
    unknownFields
    -0.69
    POSITIVE LOGITS
     can
    1.66
     CAN
    1.43
     Can
    1.37
    ocan
    1.20
    Can
    1.19
    can
    1.19
     be
    1.10
     could
    1.05
     easily
    1.05
     may
    1.01
    Activations Density 0.250%

    No Known Activations