© 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. 15110
    Prev
    Next
    INDEX
    Explanations

    phrases related to scientific measurements and detailed descriptions of physical systems

    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
    ########.
    -0.59
    rungsseite
    -0.54
    Provided
    -0.43
    iece
    -0.42
     Masses
    -0.42
    WithIOException
    -0.40
    PROVID
    -0.40
     kisses
    -0.39
     CreateTagHelper
    -0.39
    IGraphics
    -0.38
    POSITIVE LOGITS
     vicinity
    0.81
     upper
    0.73
     region
    0.65
     neighbourhood
    0.57
     neighborhood
    0.57
    upper
    0.57
     middle
    0.57
     periphery
    0.53
     inner
    0.53
     lower
    0.52
    Activations Density 1.940%

    No Known Activations