© 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. 3654
    Prev
    Next
    INDEX
    Explanations

    references to concepts and terms starting with "co-"

    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
     coastal
    -0.44
     cortical
    -0.41
     coast
    -0.40
     légales
    -0.39
    coordinate
    -0.38
    houette
    -0.37
     coster
    -0.36
     costly
    -0.36
    坐标
    -0.36
     coordinate
    -0.35
    POSITIVE LOGITS
     renang
    0.68
     Numerade
    0.59
     AssemblyTitle
    0.56
    yntaxException
    0.55
     Administrativna
    0.54
    ListItemIcon
    0.54
    таратура
    0.53
     فريبيس
    0.53
    enumi
    0.51
     تضيفلها
    0.51
    Activations Density 0.399%

    No Known Activations