© 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 EvalsExportsinterp-engineNEWAPI 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. 12459
    Prev
    Next
    INDEX
    Explanations

    references to figures, tables, and data representation in scientific writing

    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
    Figure
    -1.10
     okay
    -1.03
     Figure
    -0.96
    Okay
    -0.94
    okay
    -0.87
     Okay
    -0.85
     جدًا
    -0.82
    ًا
    -0.78
     OKAY
    -0.74
     أيضًا
    -0.74
    POSITIVE LOGITS
     Fig
    1.86
    Fig
    1.67
     Oct
    1.41
     Sept
    1.38
     Feb
    1.38
     Nov
    1.35
     Aug
    1.34
     Figs
    1.20
     Eq
    1.16
     Jan
    1.15
    Activations Density 0.756%

    No Known Activations