© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 4-GEMMASCOPE-RES-16K
    11. 2232
    Prev
    Next
    INDEX
    Explanations

    references to ordinal numbers, specifically the terms "second" and "third."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Winaray
    -0.88
    
    -0.86
     سكانية
    -0.84
    ubernur
    -0.84
     invitamos
    -0.81
    xffffff
    -0.79
    rogels
    -0.78
    kozá
    -0.77
    Pratique
    -0.77
     guste
    -0.77
    POSITIVE LOGITS
     Second
    2.01
     second
    1.99
    Second
    1.93
    second
    1.87
     SECOND
    1.84
    SECOND
    1.69
    第二
    1.47
     segunda
    1.45
     seconde
    1.44
     zweiten
    1.39
    Activations Density 0.113%

    No Known Activations