© 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. 5-GEMMASCOPE-RES-16K
    11. 15881
    Prev
    Next
    INDEX
    Explanations

    phrases related to theft and stealing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nakalista
    -0.58
    لاقات
    -0.57
    حوالہ
    -0.56
    enius
    -0.55
     remplir
    -0.55
    Portály
    -0.53
    tabli
    -0.52
     Coe
    -0.51
    eration
    -0.51
     MessageBoxIcon
    -0.49
    POSITIVE LOGITS
     stolen
    2.00
     steal
    1.90
     theft
    1.88
     stole
    1.85
     stealing
    1.85
     steals
    1.80
     thefts
    1.75
     thief
    1.71
     thieves
    1.69
    steal
    1.68
    Activations Density 0.221%

    No Known Activations