© 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-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 3694
    Prev
    Next
    INDEX
    Explanations

    the word "on"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    endregion
    -0.29
     passé
    -0.28
     Though
    -0.28
    Though
    -0.26
    ↵↵
    -0.26
     amist
    -0.26
    Sim
    -0.26
     passés
    -0.25
    localScale
    -0.24
    رام
    -0.24
    POSITIVE LOGITS
     CreateTagHelper
    0.92
     autorytatywna
    0.84
     AssemblyCulture
    0.79
    IBOutlet
    0.71
    ⤹
    0.70
     kasarigan
    0.69
     noDo
    0.68
    __(/*!
    0.67
    DataAnnotations
    0.66
     Infórmanos
    0.65
    Activations Density 0.000%

    No Known Activations