© 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-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 120389
    Prev
    Next
    INDEX
    Explanations

    phrases related to document formatting or typesetting commands

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Normdatei
    -0.60
    DoubleQuotes
    -0.56
     AssemblyCulture
    -0.56
    IBarButtonItem
    -0.56
     autorytatywna
    -0.51
    rrggbb
    -0.49
    lujah
    -0.49
     addSubview
    -0.49
     esternos
    -0.47
    dad
    -0.46
    POSITIVE LOGITS
    mord
    0.74
    setlength
    0.69
    .(*
    0.60
    ↘
    0.57
     Italijanski
    0.53
    __':
    0.48
    ngths
    0.44
    getTarget
    0.44
     naselje
    0.43
     kotlin
    0.43
    Activations Density 0.000%

    No Known Activations