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. 17-GEMMASCOPE-RES-16K
    6. 9051
    Prev
    Next
    INDEX
    Explanations

    references to programming or class structures in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ']))
    
    -0.76
    ()))
    
    -0.71
    "]))
    -0.64
    })$}
    -0.64
    '])
    
    -0.63
    ]]]
    -0.62
    ]))
    
    -0.62
    )))
    
    -0.60
    ']],
    -0.59
    ")))
    -0.58
    POSITIVE LOGITS
    IsContent
    0.78
    mybatisplus
    0.72
    \{\\
    0.70
     itſelf
    0.69
     uſe
    0.69
     reaſon
    0.67
     themſelves
    0.66
     purpoſe
    0.65
     pleaſure
    0.62
     ſp
    0.62
    Activations Density 0.078%

    No Known Activations