Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 7432
    Prev
    Next
    INDEX
    Explanations

    terms related to hiring and employment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyCulture
    -0.89
    GEBURTSDATUM
    -0.87
    parsedMessage
    -0.86
     censiti
    -0.78
    urlpatterns
    -0.77
    djangoproject
    -0.77
    inoza
    -0.76
    bukkit
    -0.76
     Audiodateien
    -0.75
    Pandora
    -0.75
    POSITIVE LOGITS
     hire
    1.46
     Hire
    1.39
    Hiring
    1.36
     hired
    1.35
     hiring
    1.35
     Hiring
    1.30
    Hire
    1.25
     hires
    1.19
     recruitment
    1.07
    Recruit
    1.04
    Activations Density 0.117%

    No Known Activations