© 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. 1403
    Prev
    Next
    INDEX
    Explanations

    phrases related to causes or conditions affecting events or decisions

    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
     '\\;'
    -0.58
    новништво
    -0.51
     certainly
    -0.46
    UserScript
    -0.45
    IActionResult
    -0.45
    SourceChecksum
    -0.43
    msgSender
    -0.43
     مرئيه
    -0.42
     deberían
    -0.42
     debería
    -0.42
    POSITIVE LOGITS
     budgetary
    0.87
     circumstances
    0.86
     lack
    0.81
    都合
    0.78
     shortage
    0.75
     prohibitive
    0.75
     illness
    0.75
     circonstances
    0.73
     covid
    0.73
     unforeseen
    0.73
    Activations Density 0.867%

    No Known Activations