© 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. 22-GEMMASCOPE-RES-16K
    6. 14241
    Prev
    Next
    INDEX
    Explanations

    expressions of love and emotional connections in various contexts

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

    "love"

    np_acts-logits-general · gemini-2.0-flash

    love stories and affection

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •Steering evals
    love

    No Comments

    Negative Logits
    ReusableCell
    -0.84
     ***!
    -0.81
    setVerticalGroup
    -0.80
    DockStyle
    -0.76
    Datuak
    -0.74
    ArgsConstructor
    -0.72
     épaules
    -0.69
    SequentialGroup
    -0.69
     MenuView
    -0.66
    )";
    
    -0.65
    POSITIVE LOGITS
     love
    0.84
    liest
    0.82
     affair
    0.81
    hate
    0.80
     LOVE
    0.80
    LOVE
    0.74
     Love
    0.68
    love
    0.67
     letters
    0.65
    Love
    0.64
    Activations Density 0.054%

    No Known Activations