© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 15549
    Prev
    Next
    INDEX
    Explanations

    technical or programming-related terms and structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    "]}
    -0.89
    ]))
    
    -0.87
    .)}
    -0.85
    "]))
    -0.85
    "])
    
    -0.83
    ]]=
    -0.80
    })$}
    -0.79
    ]}
    -0.75
    ']}
    -0.75
    )))
    
    -0.74
    POSITIVE LOGITS
     myſelf
    0.79
     Reſ
    0.76
     Majefty
    0.74
     purpoſe
    0.72
     houſe
    0.70
     himſelf
    0.69
     ſche
    0.69
     ſtate
    0.68
     themſelves
    0.68
     Houſe
    0.67
    Activations Density 0.121%

    No Known Activations