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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 19-GEMMASCOPE-RES-16K
    11. 30
    Prev
    Next
    INDEX
    Explanations

    instances of rank and social hierarchy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    FormTagHelper
    -0.53
     Völker
    -0.51
    koliv
    -0.51
    resultCode
    -0.50
    yelidikan
    -0.50
     socialista
    -0.49
     démocr
    -0.49
    enseignements
    -0.49
    genheiten
    -0.49
     einiges
    -0.48
    POSITIVE LOGITS
     staff
    1.26
     employees
    1.24
     patients
    1.04
     customers
    1.00
     clients
    0.98
     students
    0.96
     employee
    0.96
    staff
    0.96
     Staff
    0.93
     guests
    0.90
    Activations Density 0.955%

    No Known Activations