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. 3-GEMMASCOPE-RES-16K
    6. 11074
    Prev
    Next
    INDEX
    Explanations

    opening parentheses and brackets across various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     })}
    -0.81
    ]').
    -0.75
    )))
    
    -0.75
    ']);
    
    -0.71
     =>
    
    -0.69
    ]").
    -0.69
    "]);
    
    -0.67
    ]);
    
    -0.67
    "]}
    -0.66
    }])
    -0.66
    POSITIVE LOGITS
    (
    1.08
     Efq
    1.04
    ”(
    1.04
    (
    1.01
     pleaſure
    1.00
    -(
    0.96
     purpoſe
    0.96
     Majefty
    0.94
     himſelf
    0.93
     itſelf
    0.92
    Activations Density 0.543%

    No Known Activations