© 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. 3307
    Prev
    Next
    INDEX
    Explanations

    phrases related to relationships and familial dynamics

    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
     épaules
    -0.84
     négociations
    -0.84
     bénéfices
    -0.75
     pouvoirs
    -0.74
     bénévoles
    -0.73
    expandindo
    -0.72
     débats
    -0.71
     dieux
    -0.70
     attentes
    -0.69
     alliés
    -0.69
    POSITIVE LOGITS
     respective
    1.59
     respectively
    1.32
    各自
    1.32
     their
    1.30
    respective
    1.30
     reputations
    1.22
     masing
    1.20
    respectively
    1.18
    それぞれ
    1.17
     jeweils
    1.11
    Activations Density 1.202%

    No Known Activations