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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 8463
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to stealing and theft

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    partimento
    -0.59
    oluble
    -0.56
    SpringBootTest
    -0.53
     surla
    -0.52
     ràng
    -0.52
     MyApp
    -0.51
    IVersion
    -0.50
    tonode
    -0.50
     renou
    -0.50
    ulir
    -0.50
    POSITIVE LOGITS
     theft
    1.39
     steal
    1.31
     steals
    1.30
     stealing
    1.30
     stole
    1.24
     stolen
    1.21
     Theft
    1.21
    theft
    1.21
     thefts
    1.19
     thieves
    1.18
    Activations Density 0.221%

    No Known Activations