© 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. 10-GEMMASCOPE-RES-16K
    6. 6356
    Prev
    Next
    INDEX
    Explanations

    references to architectural features and formal agreements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    adaptiveStyles
    -1.02
    pexpr
    -0.71
    الإنجليزية
    -0.68
    Referencies
    -0.65
     ligiloj
    -0.65
    })));
    -0.63
    ]));
    
    -0.62
     Plots
    -0.61
    }`}>
    -0.61
    IonicModule
    -0.59
    POSITIVE LOGITS
     nor
    0.51
    hing
    0.49
     yet
    0.47
     sengaja
    0.44
     any
    0.43
    ύτε
    0.41
    zell
    0.41
    出版年
    0.40
     bewusst
    0.40
     ogóle
    0.40
    Activations Density 0.796%

    No Known Activations