© 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
    4. Residual Stream - 16k
    5. 28-GEMMASCOPE-RES-16K
    6. 3741
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical intimacy and sexual activity

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

    "lying" or "lay"

    np_acts-logits-general · gemini-2.0-flash

    lying down or in a position

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     standing
    -0.65
    Standing
    -0.63
     Standing
    -0.60
    standing
    -0.59
     berdiri
    -0.57
     stands
    -0.54
     stood
    -0.53
     stand
    -0.47
    STANDING
    -0.46
     steht
    -0.45
    POSITIVE LOGITS
     lying
    0.65
     Lying
    0.65
     pillow
    0.63
    Lying
    0.62
     pillows
    0.59
     mattress
    0.59
     rolled
    0.58
    pillow
    0.58
     snoring
    0.57
    lying
    0.56
    Activations Density 0.273%

    No Known Activations