© 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-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 9870
    Prev
    Next
    INDEX
    Explanations

    patterns or functions related to coding, specifically focusing on programming elements and their attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    '],
    
    -1.02
    8
    -0.97
    ];
    
    -0.93
    "));
    
    -0.92
    '),
    
    -0.92
    "),
    
    -0.92
    ")){
    
    -0.90
    7
    -0.90
    ],
    
    -0.89
    "],
    
    -0.88
    POSITIVE LOGITS
    ссмо
    0.51
     Efq
    0.48
     gyhoeddwyd
    0.48
     Somehow
    0.47
     dispara
    0.46
    HideFlags
    0.46
    bably
    0.46
     Grecs
    0.46
    cripción
    0.45
    طقة
    0.45
    Activations Density 0.037%

    No Known Activations