© 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. 11432
    Prev
    Next
    INDEX
    Explanations

    programming language syntax and logic statements

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

    two, deletion, and sequences

    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
    httphttps
    -0.55
     ketiga
    -0.54
     AssemblyTitle
    -0.54
    MessageTagHelper
    -0.52
    äsident
    -0.49
     queſta
    -0.47
    trone
    -0.46
     siete
    -0.46
    krieg
    -0.46
     raiſ
    -0.45
    POSITIVE LOGITS
     two
    1.09
    two
    1.04
    Two
    1.02
     Two
    0.97
     deux
    0.97
    TWO
    0.92
     TWO
    0.91
     zwei
    0.90
     двух
    0.78
     två
    0.77
    Activations Density 0.065%

    No Known Activations