Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 11856
    Prev
    Next
    INDEX
    Explanations

    method and function definitions along with their parameters in code

    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
     vian
    -0.42
    ponses
    -0.41
    ull
    -0.39
    λλά
    -0.39
     arrow
    -0.38
     esternos
    -0.37
    кра
    -0.37
    mailto
    -0.37
     Ron
    -0.37
     Vám
    -0.36
    POSITIVE LOGITS
    }")]
    0.99
     للاسماء
    0.98
    ]")]
    0.86
     بيها
    0.84
     StatefulWidget
    0.84
     StatelessWidget
    0.83
     оригіналу
    0.82
    RectangleBorder
    0.82
    __":
    
    0.81
     الحره
    0.81
    Activations Density 0.021%

    No Known Activations