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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 4338
    Prev
    Next
    INDEX
    Explanations

    references to passwords in a variety of coding contexts

    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
    ={`/
    -0.80
     Hunts
    -0.69
     Tind
    -0.66
    Tembelea
    -0.64
    ✨:
    -0.59
     Nicol
    -0.59
     Spek
    -0.58
     Ams
    -0.57
    хьтан
    -0.57
     Marker
    -0.56
    POSITIVE LOGITS
    PasswordEncoder
    1.42
     password
    1.33
     Password
    1.26
     getPassword
    1.26
     passwords
    1.18
    getPassword
    1.13
    Password
    1.08
    password
    1.06
    PASSWORD
    1.05
     PASSWORD
    1.03
    Activations Density 0.034%

    No Known Activations