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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 18-GEMMASCOPE-RES-16K
    6. 14632
    Prev
    Next
    INDEX
    Explanations

    phrases related to employment and job transitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    around "job" or "employment"

    np_acts-logits-general · gemini-2.0-flash

    employment and finding new jobs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    parsedMessage
    -0.84
    Lähteet
    -0.78
    NameInMap
    -0.76
    LookAnd
    -0.69
     فريبيس
    -0.67
    rungsseite
    -0.63
    uxxxx
    -0.61
    出版年
    -0.60
    Према
    -0.60
    存于互联网档案馆
    -0.60
    POSITIVE LOGITS
     jobs
    2.11
     job
    1.98
     Jobs
    1.72
    jobs
    1.72
    job
    1.68
    Job
    1.61
     Job
    1.61
    Jobs
    1.60
     employment
    1.54
     JOBS
    1.50
    Activations Density 0.225%

    No Known Activations