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. 3805
    Prev
    Next
    INDEX
    Explanations

    HTML block elements and components related to user interface rendering

    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
    ectoria
    -0.56
    хьтан
    -0.55
    aarrggbb
    -0.54
    buster
    -0.52
    urahan
    -0.52
    asthan
    -0.50
    lblNewLabel
    -0.50
     TERM
    -0.48
     Munch
    -0.47
    cloak
    -0.47
    POSITIVE LOGITS
    </blockquote>
    1.99
    })*/
    0.90
    \]
    0.89
    </code>
    0.84
    `;
    
    0.83
    httphttps
    0.82
    }".
    0.82
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.81
     Tapatalk
    0.80
    })()
    0.79
    Activations Density 0.008%

    No Known Activations