© 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-2-9B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 3342
    Prev
    Next
    INDEX
    Explanations

    references to the concept of existence and identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 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
     autorytatywna
    -0.98
     arşivlendi
    -0.77
    AddTagHelper
    -0.76
    ValueStyle
    -0.75
     jsPsych
    -0.75
     MainAxisSize
    -0.74
    webElementXpaths
    -0.73
     للمعارف
    -0.70
     ErrIntOverflow
    -0.70
    featureID
    -0.70
    POSITIVE LOGITS
    agisse
    0.37
    Naissance
    0.33
    采访
    0.32
     maupun
    0.32
     quaisquer
    0.32
    不论
    0.30
    Whatever
    0.30
     evolved
    0.30
    ULD
    0.29
     sufren
    0.29
    Activations Density 0.158%

    No Known Activations