© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 8483
    Prev
    Next
    INDEX
    Explanations

    references to specific products or materials related to comfort

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

    about sleeping and bedding

    np_acts-logits-general · gemini-2.0-flash

    bed and seat sections

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
    dBm
    -0.63
     civile
    -0.59
    ArrowToggle
    -0.57
     TAMBIÉN
    -0.55
     chopsticks
    -0.55
     civil
    -0.53
     Frontera
    -0.53
    antism
    -0.52
     sunglasses
    -0.52
     виправивши
    -0.52
    POSITIVE LOGITS
     mattress
    1.19
     pillow
    1.11
     mattresses
    1.06
     sleep
    1.04
     Mattress
    1.04
     pillows
    1.03
     Sleep
    1.02
     Pillow
    0.97
     sleeping
    0.91
     sleeps
    0.91
    Activations Density 0.156%

    No Known Activations