Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 3595
    Prev
    Next
    INDEX
    Explanations

    references to love and personal connections in relationships

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

    Followed by word "love"

    np_acts-logits-general · gemini-2.0-flash

    fall in love

    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
    Not in Any Lists

    No Comments

    Negative Logits
    jmniej
    -0.56
     StringTokenizer
    -0.55
    SequentialGroup
    -0.51
     NUKAT
    -0.50
     ProtoMessage
    -0.50
    áus
    -0.49
     egiten
    -0.48
    VIAF
    -0.47
     iconLine
    -0.47
     CURIAM
    -0.47
    POSITIVE LOGITS
     love
    3.46
    love
    2.89
     Love
    2.81
    Love
    2.71
     LOVE
    2.70
     loves
    2.50
    LOVE
    2.49
    loves
    2.11
     loving
    2.06
     loved
    2.04
    Activations Density 0.213%

    No Known Activations