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. 1-GEMMASCOPE-RES-16K
    6. 13750
    Prev
    Next
    INDEX
    Explanations

    terms related to career and professional development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    FormTagHelper
    -0.75
    Hozzáférés
    -0.66
    fromnode
    -0.66
    Optional
    -0.65
    ?>">
    -0.62
     bisog
    -0.62
    AutoresizingMask
    -0.61
     tentative
    -0.60
    optional
    -0.59
    WebElementEntity
    -0.59
    POSITIVE LOGITS
     career
    2.23
     careers
    2.08
    career
    1.94
     Career
    1.92
    Career
    1.83
     CAREER
    1.68
     Careers
    1.50
    careers
    1.47
     carrière
    1.46
    Careers
    1.42
    Activations Density 0.071%

    No Known Activations