© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 871
    Prev
    Next
    INDEX
    Explanations

    references to secretarial positions and titles

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

    "Secretary" or "Secretary-General"

    np_acts-logits-general · gemini-2.0-flash

    secretary general

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     surla
    -0.60
     noDo
    -0.53
    Personensuche
    -0.52
     propOrder
    -0.51
    HostException
    -0.51
     חיצוניים
    -0.50
    RTSC
    -0.48
    يميديا
    -0.45
    yntaxException
    -0.45
    IntoConstraints
    -0.44
    POSITIVE LOGITS
     Secretary
    1.66
     secretary
    1.63
    Secretary
    1.59
     SECRETARY
    1.44
    secretary
    1.41
     secretaries
    1.29
     Secretaries
    1.24
     secrétaire
    1.13
     Secrétaire
    1.12
     Sekret
    1.09
    Activations Density 0.173%

    No Known Activations