© 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
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 14261
    Prev
    Next
    INDEX
    Explanations

    references to babies and newborns

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

    the word "baby" in various contexts.

    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
    tagHelperRunner
    -0.51
    suporte
    -0.42
     Wirkungen
    -0.39
     příjem
    -0.38
    RuleContext
    -0.37
    ValueGenerated
    -0.37
    ViewFeatures
    -0.37
    newInstance
    -0.36
    HasForeignKey
    -0.36
    sbury
    -0.35
    POSITIVE LOGITS
    Baby
    0.75
    doll
    0.74
     Baby
    0.68
    baby
    0.66
     boomers
    0.65
    BABY
    0.64
     baby
    0.63
     Jefus
    0.59
     sitter
    0.58
     doll
    0.57
    Activations Density 0.085%

    No Known Activations