© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 11433
    Prev
    Next
    INDEX
    Explanations

    mentions of family relationships, particularly focusing on sons and daughters

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

    a son or daughter

    np_acts-logits-general · gemini-2.0-flash

    sons and daughters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    HtmlAttribute
    -0.59
    ErrUnexpectedEOF
    -0.53
    extAlignment
    -0.50
    DataAnnotations
    -0.50
     nevoie
    -0.50
    addPreferred
    -0.49
     الوطنيه
    -0.48
     UIAlert
    -0.48
    Autoritní
    -0.48
    irvana
    -0.48
    POSITIVE LOGITS
     son
    1.56
     daughter
    1.52
     Daughter
    1.44
    Daughter
    1.41
     Son
    1.39
     sons
    1.34
    Son
    1.32
     daughters
    1.23
    daughter
    1.20
     Sons
    1.19
    Activations Density 0.177%

    No Known Activations