© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 15564
    Prev
    Next
    INDEX
    Explanations

    the word "senior" and related terms, indicating a focus on seniority or hierarchy in professional contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    脚注の使い方
    -0.73
    %)$
    -0.71
    olanda
    -0.64
    pham
    -0.60
     gustó
    -0.58
    ientôt
    -0.56
     conoc
    -0.56
    網址
    -0.56
     Usaha
    -0.56
    bruik
    -0.56
    POSITIVE LOGITS
     senior
    2.23
     Senior
    2.19
    Senior
    2.08
    SENIOR
    2.08
    senior
    2.08
     SENIOR
    2.06
     seniors
    1.88
     Seniors
    1.72
    Seniors
    1.63
     junior
    1.48
    Activations Density 0.059%

    No Known Activations