© 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. 7194
    Prev
    Next
    INDEX
    Explanations

    references to health-related studies and surveys involving children and families

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

    academic and research study descriptions with statistical data and methodological details.

    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
     virke
    -0.36
     humble
    -0.35
    Przypisy
    -0.32
    ="@+
    -0.31
    setModel
    -0.31
    \{\\
    -0.30
     Cul
    -0.30
     feed
    -0.29
    ClientSize
    -0.29
     ahli
    -0.28
    POSITIVE LOGITS
     Household
    0.79
     household
    0.75
     Survey
    0.75
    Household
    0.74
     survey
    0.71
     households
    0.70
    household
    0.69
    Survey
    0.68
     interviewer
    0.67
    tanleria
    0.64
    Activations Density 0.785%

    No Known Activations