© 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. 38873
    Prev
    Next
    INDEX
    Explanations

    code structure elements related to classes and constructors in programming languages

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

    code constructs constructor script

    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
    ()};
    -0.43
    \"");
    -0.42
    MessageOf
    -0.40
    請繼續往下閱讀
    -0.40
    )");
    
    -0.39
    ">\
    -0.39
    "");
    -0.38
    {
    
    
    -0.38
    +");
    -0.38
    "]));
    -0.38
    POSITIVE LOGITS
     miniaturka
    0.52
     ferons
    0.52
     nakalista
    0.48
    exitRule
    0.46
    Rptr
    0.44
     privado
    0.44
     privées
    0.43
    RegressionTest
    0.43
     quelcon
    0.42
     deviceId
    0.42
    Activations Density 0.001%

    No Known Activations