© 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. 37-GEMMASCOPE-RES-16K
    11. 7376
    Prev
    Next
    INDEX
    Explanations

    identifiers and keywords related to programming or markup languages

    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
    quiel
    -0.45
    uose
    -0.38
    zed
    -0.37
    SOUNDBITE
    -0.36
    lichung
    -0.36
     Rates
    -0.35
     phần
    -0.35
     saling
    -0.35
     Sementara
    -0.35
    破
    -0.35
    POSITIVE LOGITS
    rungsseite
    0.50
     Roskov
    0.49
    WriteBarrier
    0.48
     itſelf
    0.48
    تقاوى
    0.47
     Monfieur
    0.45
     Houſe
    0.45
    ſelves
    0.44
    URLException
    0.44
    ➯
    0.44
    Activations Density 0.118%

    No Known Activations