© 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. 38-GEMMASCOPE-RES-16K
    11. 8095
    Prev
    Next
    INDEX
    Explanations

    scientific terms related to chemical processes and the presence of metals in environmental 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
     linkovi
    -0.60
     noDo
    -0.51
     estekak
    -0.48
     Urea
    -0.47
    RTLR
    -0.44
     oprot
    -0.43
     esternos
    -0.42
     Methanol
    -0.41
     GenerationType
    -0.41
     methane
    -0.41
    POSITIVE LOGITS
     trace
    0.78
     elements
    0.74
     element
    0.73
     metals
    0.73
    元素
    0.68
     metal
    0.65
    Trace
    0.64
     Elements
    0.62
     Trace
    0.62
    trace
    0.61
    Activations Density 0.993%

    No Known Activations