© 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. 38-GEMMASCOPE-RES-16K
    11. 12857
    Prev
    Next
    INDEX
    Explanations

    references to extreme pressure conditions and their effects on materials

    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
    itieren
    -0.31
     Kön
    -0.30
    ":[{
    -0.29
     uncin
    -0.28
     {#
    -0.28
     Portage
    -0.28
     agrí
    -0.27
     Pup
    -0.27
    hdashline
    -0.27
    igable
    -0.27
    POSITIVE LOGITS
     press
    3.08
     pressure
    3.02
     Press
    2.94
    Press
    2.86
    press
    2.84
     PRESS
    2.81
     Pressure
    2.72
    Pressure
    2.70
    PRESS
    2.70
    pressure
    2.67
    Activations Density 1.168%

    No Known Activations