© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 8831
    Prev
    Next
    INDEX
    Explanations

    phrases related to career development and achievements

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

    Preceding "career" or related to "career"

    np_acts-logits-general · gemini-2.0-flash

    talking about a person's career

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bootstrapcdn
    -0.62
    ']?>
    -0.54
    ofType
    -0.53
    BASEPATH
    -0.49
    vaadin
    -0.49
    toplasmic
    -0.46
    του
    -0.46
    ettu
    -0.44
    گرام
    -0.44
    GeneratedMessage
    -0.44
    POSITIVE LOGITS
     career
    2.48
    career
    2.09
     careers
    2.02
     carrière
    1.80
     Career
    1.77
     CAREER
    1.77
    Career
    1.74
     carriera
    1.65
     Karriere
    1.58
    CAREER
    1.51
    Activations Density 0.238%

    No Known Activations