© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 10486
    Prev
    Next
    INDEX
    Explanations

    references to duration and experience in a professional context

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

    Number of years in a profession

    np_acts-logits-general · gemini-2.0-flash

    years of experience

    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
    GEBURTSDATUM
    -0.86
     חיצוניים
    -0.84
    rungsseite
    -0.84
    脚注の使い方
    -0.76
    IContainer
    -0.69
     disambiguazione
    -0.69
    posedge
    -0.68
    下载附件
    -0.67
     ModelExpression
    -0.67
    ⓧ
    -0.67
    POSITIVE LOGITS
     wonderful
    0.55
    wonderful
    0.53
     diber
    0.49
    neer
    0.49
    qual
    0.47
     clients
    0.47
     meritorious
    0.47
     heureux
    0.47
     honorable
    0.46
    ρίες
    0.46
    Activations Density 0.081%

    No Known Activations