© 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. 7850
    Prev
    Next
    INDEX
    Explanations

    questions and expressions of confusion or uncertainty

    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
     mijn
    -1.21
     my
    -1.21
     myself
    -1.16
     meiner
    -1.15
     minha
    -1.12
     meine
    -1.10
     meu
    -1.09
     meinem
    -1.09
     moje
    -1.08
     mojej
    -1.06
    POSITIVE LOGITS
     I
    1.60
     i
    0.88
    Билгалдахарш
    0.46
    Autoritní
    0.41
    yntaxException
    0.41
    I
    0.39
    principalTable
    0.39
    inheritDoc
    0.38
     دریافت‌شده
    0.38
    Viited
    0.38
    Activations Density 1.053%

    No Known Activations