© 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-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 4525
    Prev
    Next
    INDEX
    Explanations

    references to comfort and comfort-related qualities in various contexts

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

    physical or emotional comfort

    np_acts-logits-general · gemini-2.0-flash

    comfort and comfortable

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     MutableLiveData
    -0.43
     Yahya
    -0.40
     leader
    -0.40
     Jay
    -0.40
    DataSnapshot
    -0.39
     juist
    -0.39
     Yeats
    -0.38
     new
    -0.37
    สา
    -0.37
     name
    -0.37
    POSITIVE LOGITS
    Comfort
    1.30
     Comfort
    1.26
    comfort
    1.25
     COMFORT
    1.22
     comfort
    1.18
    Comfortable
    1.15
     Comfortable
    1.13
    comfortable
    1.11
     comfortable
    1.06
     comforts
    1.04
    Activations Density 0.031%

    No Known Activations