© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 2083
    Prev
    Next
    INDEX
    Explanations

    terms related to political ideology and critique

    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
     telle
    -0.68
     roja
    -0.64
     saco
    -0.63
     buenos
    -0.63
     reales
    -0.60
     desgracia
    -0.59
     furia
    -0.58
     brune
    -0.58
     doloroso
    -0.58
     morales
    -0.57
    POSITIVE LOGITS
    kháu
    0.83
    leth
    0.79
    XmlAccessType
    0.78
    ghijklmnop
    0.77
    Boxscore
    0.76
    thor
    0.75
    YourGuide
    0.73
    kits
    0.72
     själ
    0.72
    طبيق
    0.71
    Activations Density 1.227%

    No Known Activations