© 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. 3-GEMMASCOPE-RES-16K
    11. 1595
    Prev
    Next
    INDEX
    Explanations

    referring pronouns or phrases indicating relationships among people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IUrlHelper
    -0.83
    ImageContext
    -0.81
     esternos
    -0.75
    AnchorStyles
    -0.74
    Népesség
    -0.71
    NameInMap
    -0.70
    AndEndTag
    -0.67
    клопе
    -0.67
     gynhyrchwyd
    -0.67
     }{@
    -0.66
    POSITIVE LOGITS
    AlterField
    0.61
     iprot
    0.52
    Quien
    0.51
    ندما
    0.51
    Αν
    0.44
    要想
    0.43
    osoever
    0.42
     quem
    0.42
    вшим
    0.42
     jsPsych
    0.42
    Activations Density 0.297%

    No Known Activations