© 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-2-9B
    7. Residual Stream - 16k
    9. 36-GEMMASCOPE-RES-16K
    11. 11127
    Prev
    Next
    INDEX
    Explanations

    terms related to human resources and management functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     anún
    -0.42
    ilíbrio
    -0.40
    plet
    -0.40
    Tē
    -0.39
     bezeichneter
    -0.39
     newOwner
    -0.38
    tonode
    -0.38
     decorados
    -0.38
    ateness
    -0.37
     الرياضيه
    -0.37
    POSITIVE LOGITS
     department
    1.04
     team
    0.99
     staff
    0.90
     dept
    0.87
     departments
    0.86
    department
    0.81
     teams
    0.78
     personnel
    0.76
     Abteilung
    0.76
    team
    0.72
    Activations Density 0.539%

    No Known Activations