© 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 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. 6627
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate an increase or addition

    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
    QMetaType
    -0.45
     يتيمه
    -0.45
     cherchés
    -0.43
    writeFieldEnd
    -0.41
    LikeLike
    -0.40
    TagMode
    -0.40
     Fas
    -0.36
    Tembelea
    -0.36
    withOpacity
    -0.35
     AssemblyVersion
    -0.35
    POSITIVE LOGITS
     importantly
    1.19
     surprisingly
    0.92
     interestingly
    0.89
    prisingly
    0.76
     specifically
    0.72
     remarkably
    0.71
     überras
    0.68
     amazingly
    0.67
     Importantly
    0.67
     pertin
    0.66
    Activations Density 0.231%

    No Known Activations