© 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. 11-GEMMASCOPE-RES-16K
    6. 14530
    Prev
    Next
    INDEX
    Explanations

    programming language syntax elements and structure in code snippets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     DialogInterface
    -0.87
     onAnimation
    -0.82
     CreateTagHelper
    -0.77
     '\\;'
    -0.77
    principalColumn
    -0.71
     TextInputType
    -0.70
    AnchorStyles
    -0.70
    mybatisplus
    -0.69
    ecap
    -0.67
    berdayakan
    -0.67
    POSITIVE LOGITS
    </em>
    0.83
    </i>
    0.65
    </code>
    0.65
    CharStream
    0.63
            
    0.61
    </u>
    0.58
           
    0.56
         
    0.55
               
    0.55
    </strong>
    0.54
    Activations Density 0.483%

    No Known Activations