© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 38-GEMMASCOPE-RES-16K
    11. 12363
    Prev
    Next
    INDEX
    Explanations

    chemical concentrations and measurements in scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Халык
    -0.37
    webElementXpaths
    -0.34
     Imperial
    -0.34
    pædia
    -0.33
    BFS
    -0.33
    Mars
    -0.33
    Missing
    -0.33
    굿
    -0.32
     BF
    -0.32
     Virginia
    -0.32
    POSITIVE LOGITS
     μ
    0.96
     µ
    0.89
    μ
    0.84
     micro
    0.82
    µ
    0.79
     mikro
    0.79
     Mikro
    0.69
    マイクロ
    0.67
    
    0.66
    micro
    0.66
    Activations Density 1.085%

    No Known Activations