© 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. 37-GEMMASCOPE-RES-16K
    11. 1786
    Prev
    Next
    INDEX
    Explanations

    terms related to health, safety, and potential hazards

    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
     agradec
    -0.40
     gratefully
    -0.40
     благода
    -0.40
    楽しみです
    -0.38
     grâce
    -0.35
    真好
    -0.35
    Hentet
    -0.35
    就可以了
    -0.35
     impressed
    -0.34
    就行了
    -0.34
    POSITIVE LOGITS
     causing
    2.08
    causing
    1.84
     menyebabkan
    1.67
     mengakibatkan
    1.66
    導致
    1.63
    导致
    1.56
     forcing
    1.52
     resulting
    1.52
     causando
    1.51
     khiến
    1.44
    Activations Density 2.384%

    No Known Activations