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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 5-GEMMASCOPE-RES-16K
    6. 11975
    Prev
    Next
    INDEX
    Explanations

    symbols and notation related to mathematical functions and error metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RectangleBorder
    -0.74
     ModelExpression
    -0.66
    aarrggbb
    -0.65
     Vikipedi
    -0.65
     Réponses
    -0.57
     ģ
    -0.54
    ichthys
    -0.53
    hoodie
    -0.53
    花板
    -0.51
    opc
    -0.51
    POSITIVE LOGITS
    ^(@)
    0.84
    )";
    
    0.80
     $_"
    0.80
    "]);
    
    0.79
     ]
    
    0.79
    ']
    
    0.78
     "];
    0.75
    ydable
    0.75
    _
    
    0.74
    )");
    
    0.73
    Activations Density 0.674%

    No Known Activations