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. 4-GEMMASCOPE-RES-16K
    6. 10811
    Prev
    Next
    INDEX
    Explanations

    terms related to career planning and development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     initWithFrame
    -0.59
    llus
    -0.55
    ærk
    -0.55
    elcome
    -0.53
    bereits
    -0.52
    spreis
    -0.52
    protocols
    -0.51
    herzog
    -0.48
    ുള്ള
    -0.48
     muñeco
    -0.48
    POSITIVE LOGITS
     career
    1.90
    career
    1.61
     careers
    1.57
     Career
    1.53
    Career
    1.50
     CAREER
    1.47
     carrière
    1.35
     Karriere
    1.27
     Careers
    1.25
    CAREER
    1.22
    Activations Density 0.480%

    No Known Activations