© 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. 4723
    Prev
    Next
    INDEX
    Explanations

    instances of the word "don" 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 @ 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
    <bos>
    -0.84
    ValueStyle
    -0.70
    Msp
    -0.67
     Мексичка
    -0.61
     CURIAM
    -0.59
    Referencie
    -0.59
    BASEPATH
    -0.58
    newArrayList
    -0.58
    WithIOException
    -0.57
    strokeStyle
    -0.55
    POSITIVE LOGITS
     don
    3.00
    don
    2.61
     DON
    2.53
    Don
    2.52
     Don
    2.42
    DON
    2.33
     aren
    1.69
     Dons
    1.68
     doesn
    1.67
     haven
    1.59
    Activations Density 0.068%

    No Known Activations