© 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. 20292
    Prev
    Next
    INDEX
    Explanations

    structured data formats related to device and software specifications

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

    mathematical expressions and separators

    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
    '>
    
    -0.65
    transQ
    -0.62
    SequentialGroup
    -0.60
    $")
    -0.59
     '*')
    -0.57
    ]";
    -0.54
    )");
    
    -0.54
    )";
    
    -0.54
    ."</
    -0.53
     '
    
    -0.52
    POSITIVE LOGITS
    ________________
    0.84
     AssemblyCulture
    0.67
    ________
    0.63
    ___
    0.62
    _______________
    0.61
    ______
    0.60
    ____
    0.60
    _______
    0.60
     ________
    0.60
    ................
    0.57
    Activations Density 0.068%

    No Known Activations