© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 64055
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and certain structural tokens in complex documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    lions, produced, cumulative

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    Txn
    -0.40
     Monfieur
    -0.39
    lename
    -0.38
    ówno
    -0.37
     engagé
    -0.37
    zeugt
    -0.35
    wegian
    -0.35
    launch
    -0.35
    Commit
    -0.34
    はじめに
    -0.34
    POSITIVE LOGITS
    IntoConstraints
    0.71
     Normdatei
    0.69
    DeleteBehavior
    0.63
     NSCoder
    0.56
    InSection
    0.54
    centralwidget
    0.51
     betweenstory
    0.48
    icitis
    0.48
     незавершена
    0.46
     Biôgrafia
    0.46
    Activations Density 0.001%

    No Known Activations