© 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. 12164
    Prev
    Next
    INDEX
    Explanations

    information related to measurement accuracy and error 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
    expandindo
    -0.50
     ProtoMessage
    -0.34
     defaultstate
    -0.34
    zystać
    -0.34
     düşünü
    -0.33
    ViewFeatures
    -0.33
     Mah
    -0.31
     disposición
    -0.31
    IContainer
    -0.31
     nowo
    -0.30
    POSITIVE LOGITS
     accurate
    3.03
     accuracy
    2.98
    accurate
    2.70
     Accurate
    2.66
    Accurate
    2.63
     ACCUR
    2.59
     Accuracy
    2.59
     accurately
    2.42
    accuracy
    2.41
    Accuracy
    2.39
    Activations Density 1.145%

    No Known Activations