© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 7275
    Prev
    Next
    INDEX
    Explanations

    discussions about diapering concerns and practices for babies

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

    words and phrases related to baby diapers and diapering products.

    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
    IntoConstraints
    -0.76
    jspb
    -0.60
     Schülern
    -0.52
    WriteBarrier
    -0.52
    ########.
    -0.50
    enderror
    -0.50
     مرئيه
    -0.49
    Selfer
    -0.48
    students
    -0.48
    Captor
    -0.48
    POSITIVE LOGITS
     baby
    1.94
     Baby
    1.84
    Baby
    1.78
    baby
    1.71
     infant
    1.68
     BABY
    1.66
     Babies
    1.59
    BABY
    1.57
     babies
    1.56
     Infant
    1.55
    Activations Density 0.601%

    No Known Activations