© 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. 1341
    Prev
    Next
    INDEX
    Explanations

    concepts related to measurement units and physical definitions

    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
    matri
    -0.40
    melin
    -0.40
    anato
    -0.38
    accès
    -0.38
    Erstellt
    -0.38
     matri
    -0.36
     watermark
    -0.36
    piram
    -0.36
    onek
    -0.36
     Océ
    -0.36
    POSITIVE LOGITS
     acceleration
    0.74
     motion
    0.73
     Acceleration
    0.71
     Newton
    0.68
     MOTION
    0.65
     Motion
    0.65
    Newton
    0.64
     velocity
    0.63
     aceler
    0.62
    Acceleration
    0.62
    Activations Density 0.522%

    No Known Activations