© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 558
    Prev
    Next
    INDEX
    Explanations

    expressions related to comfort and discomfort

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    instances of the word "comfortable" associated with high activation values.

    oai_token-act-pair · gpt-4-turboTriggered by @johnny
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bootstrapcdn
    -0.78
     giudi
    -0.70
    клопе
    -0.69
     postIndex
    -0.69
    iço
    -0.68
    cshtml
    -0.67
    sieu
    -0.67
     BorderLayout
    -0.67
    UMBIA
    -0.66
     gynhyrchwyd
    -0.65
    POSITIVE LOGITS
     comfortable
    2.73
     Comfortable
    2.32
    comfortable
    2.30
    Comfortable
    2.23
     comfy
    2.21
     comfort
    2.13
     uncomfortable
    2.07
     COMFORT
    2.04
     comfortably
    2.01
     confortable
    1.97
    Activations Density 0.136%

    No Known Activations