© 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. 3807
    Prev
    Next
    INDEX
    Explanations

    structural components and functions related to data forms and queries within programming or technical contexts

    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
    <_>
    -0.36
     تضيفلها
    -0.36
    ési
    -0.33
     if
    -0.31
    FailureListener
    -0.31
     for
    -0.31
    下手
    -0.30
     إن
    -0.30
    ras
    -0.29
    ).__
    -0.29
    POSITIVE LOGITS
     For
    1.31
     By
    1.27
     To
    1.22
     At
    1.18
     From
    1.17
     On
    1.11
    For
    1.07
     With
    1.02
     Untuk
    1.00
    By
    0.99
    Activations Density 0.599%

    No Known Activations