© 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. 31-GEMMASCOPE-RES-16K
    6. 7805
    Prev
    Next
    INDEX
    Explanations

    references to parental attributes and relationships in the context of children’s legitimacy

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

    references to parental relationships and family composition characteristics.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     grandfather
    -0.45
     uncle
    -0.43
    grandfather
    -0.42
     Uncle
    -0.41
    씨
    -0.38
     Grandfather
    -0.36
    uomo
    -0.35
    Uncle
    -0.33
    prom
    -0.33
     başına
    -0.33
    POSITIVE LOGITS
     parents
    2.03
     Parents
    1.72
    Parents
    1.68
    parents
    1.61
     PARENTS
    1.51
     parent
    1.45
     Eltern
    1.45
     ouders
    1.41
     parental
    1.38
    父母
    1.37
    Activations Density 0.215%

    No Known Activations