© 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. 4425
    Prev
    Next
    INDEX
    Explanations

    references to actions indicating adjustments or changes in mechanical or operational systems

    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
     surla
    -0.56
    ViewFeatures
    -0.43
    μφωνα
    -0.39
    AndroidJUnit
    -0.38
     يتيمه
    -0.38
     odpad
    -0.38
     disambiguazione
    -0.38
    RTEX
    -0.36
    FailureListener
    -0.35
     فريبيس
    -0.35
    POSITIVE LOGITS
     adjustment
    2.22
     adjusting
    2.20
     adjust
    2.20
    Adjust
    2.06
     adjusted
    2.05
     Adjust
    2.03
     adjusts
    2.02
     adjustments
    1.99
    adjust
    1.96
     Adjusting
    1.96
    Activations Density 1.000%

    No Known Activations