© 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. 9249
    Prev
    Next
    INDEX
    Explanations

    statistical data and results related to censuses or counts

    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
     незавершена
    -0.87
    __':
    
    -0.82
     Вікі
    -0.80
    __':
    -0.78
    tagHelperRunner
    -0.75
     للاسماء
    -0.74
    UrlResolution
    -0.74
    yntaxException
    -0.72
     متعلقه
    -0.72
    IMPORTED
    -0.71
    POSITIVE LOGITS
     very
    0.88
    very
    0.69
     begging
    0.68
     Very
    0.66
    Very
    0.62
     VERY
    0.59
     muy
    0.51
    的很
    0.51
    țin
    0.49
    VERY
    0.49
    Activations Density 0.209%

    No Known Activations