© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 4170
    Prev
    Next
    INDEX
    Explanations

    references or citations within a text

    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
    ="#">
    -0.55
     landing
    -0.55
     kilometres
    -0.53
     descending
    -0.53
    (;;)
    -0.52
    ügen
    -0.51
    ViewFeatures
    -0.51
    Dés
    -0.50
     indietro
    -0.50
    Chrys
    -0.49
    POSITIVE LOGITS
    tagHelperRunner
    0.93
    extAlignment
    0.78
     nawr
    0.69
    لينكات
    0.67
    الإنجليزية
    0.63
     Infórmanos
    0.60
    IVEREF
    0.60
     مشين
    0.59
    GIVEREF
    0.58
     متعلقه
    0.58
    Activations Density 0.133%

    No Known Activations