© 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-2-2B
    7. Residual Stream - 16k
    9. 1-GEMMASCOPE-RES-16K
    11. 7807
    Prev
    Next
    INDEX
    Explanations

    descriptors of friendly and courteous interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Aufs
    -0.57
     publicidad
    -0.54
    sohn
    -0.54
     cometh
    -0.54
     pubblicità
    -0.52
     McKe
    -0.52
     paraître
    -0.51
     nokt
    -0.51
     imprend
    -0.51
     hemato
    -0.50
    POSITIVE LOGITS
     friendly
    2.82
     Friendly
    2.61
    friendly
    2.54
    Friendly
    2.52
     friendliness
    1.72
     unfriendly
    1.68
     freundlichen
    1.34
     vriende
    1.34
    友好
    1.28
     freund
    1.26
    Activations Density 0.040%

    No Known Activations