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. 4-GEMMASCOPE-RES-16K
    6. 11594
    Prev
    Next
    INDEX
    Explanations

    references to studies or significant findings in medical or health-related contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Newberry
    -0.86
     Bex
    -0.82
     BoxDecoration
    -0.80
     BoxFit
    -0.80
     Ith
    -0.77
     utafitiHapana
    -0.74
    InputBorder
    -0.73
     Perspek
    -0.73
    ed
    -0.72
    Lycka
    -0.72
    POSITIVE LOGITS
    ↵↵↵
    0.87
    )))),
    0.82
    }})
    0.74
     referrerpolicy
    0.73
    ')")
    0.70
    </strong>
    0.68
    ])
    0.67
    ']))
    
    0.67
     ]
    
    0.66
    '])
    
    0.65
    Activations Density 0.057%

    No Known Activations