© 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-2-9B
    7. Residual Stream - 16k
    9. 40-GEMMASCOPE-RES-16K
    11. 5105
    Prev
    Next
    INDEX
    Explanations

    references to job roles in a retail or service context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     masakan
    -0.46
    SpringRunner
    -0.46
    InputBorder
    -0.43
    autorest
    -0.42
    Übernach
    -0.41
     getParent
    -0.41
    perties
    -0.40
    GrantedAuthority
    -0.40
    resid
    -0.40
    -------
    -0.40
    POSITIVE LOGITS
     counter
    1.48
     counters
    1.23
    counter
    1.18
     Counter
    1.17
     cashier
    1.14
    Counter
    1.09
     COUNTER
    1.06
     Counters
    1.00
     desk
    1.00
     clerk
    1.00
    Activations Density 0.283%

    No Known Activations