© 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. 37-GEMMASCOPE-RES-16K
    11. 4522
    Prev
    Next
    INDEX
    Explanations

    phrases that discuss differences or statistical significance in data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UESDAY
    -0.33
    Cyfarwyddwr
    -0.32
    الدراسه
    -0.32
     الحره
    -0.30
     createSprite
    -0.27
    飽
    -0.27
    TagNumber
    -0.26
     متعلقه
    -0.26
    原始内容存档
    -0.25
    //
    -0.25
    POSITIVE LOGITS
     difference
    3.70
     differences
    3.30
    difference
    3.27
     Difference
    3.20
    Difference
    3.13
     Differences
    3.02
     DIFFERENCE
    2.95
    Differences
    2.94
    differences
    2.89
     différence
    2.88
    Activations Density 2.334%

    No Known Activations