© 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. 33-GEMMASCOPE-RES-16K
    11. 9305
    Prev
    Next
    INDEX
    Explanations

    references to the term "the" and variations of the word that appear in a context associated with importance or prominence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MigrationBuilder
    -0.60
     Taktlose
    -0.57
    Atsauces
    -0.50
    ByVersion
    -0.48
    SBATCH
    -0.48
     queſta
    -0.47
    WriteTagHelper
    -0.47
     actionMode
    -0.46
     NSCoder
    -0.46
     resourceCulture
    -0.45
    POSITIVE LOGITS
     likes
    0.88
     legendary
    0.72
     aforementioned
    0.69
     inim
    0.68
    likes
    0.64
     aptly
    0.63
    legendary
    0.60
     late
    0.60
     incomparable
    0.58
     afore
    0.57
    Activations Density 0.494%

    No Known Activations