© 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. 38-GEMMASCOPE-RES-16K
    11. 7685
    Prev
    Next
    INDEX
    Explanations

    verbs related to actions and processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    guisement
    -0.31
    ívne
    -0.29
     igjen
    -0.29
     virksom
    -0.29
    ندران
    -0.28
     falda
    -0.28
     místě
    -0.28
    Попис
    -0.27
     dår
    -0.27
     hjælp
    -0.27
    POSITIVE LOGITS
     through
    3.48
    through
    3.02
    Through
    2.97
     Through
    2.95
     THROUGH
    2.81
    THROUGH
    2.55
     attraverso
    2.34
     thru
    2.33
     через
    2.20
     melalui
    2.14
    Activations Density 1.682%

    No Known Activations