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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 75104
    Prev
    Next
    INDEX
    Explanations

    information related to marital history and family relationships

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

    marriage and divorce

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     calib
    -0.57
    parsedMessage
    -0.55
    الحياه
    -0.54
     impert
    -0.54
     DSA
    -0.52
     dedu
    -0.52
    Correspond
    -0.52
     Jove
    -0.50
     Peers
    -0.50
     stabilis
    -0.49
    POSITIVE LOGITS
     divorced
    0.46
     libremente
    0.46
     esposa
    0.45
     guerras
    0.44
     librement
    0.43
     autrefois
    0.43
     suaminya
    0.43
     bolsillos
    0.42
     divorce
    0.42
     formales
    0.42
    Activations Density 0.023%

    No Known Activations