Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 17-GEMMASCOPE-RES-16K
    6. 7187
    Prev
    Next
    INDEX
    Explanations

    document structure and formatting elements, specifically recognizing the beginning of a document

    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
     onAnimation
    -0.78
    +#+
    -0.78
    #+#
    -0.71
     cdti
    -0.71
    berdayakan
    -0.69
    viembre
    -0.68
    bkz
    -0.67
     MatDialog
    -0.67
     –,
    -0.66
     whiteColor
    -0.65
    POSITIVE LOGITS
    <eos>
    1.09
    ↵
    0.61
      
    0.60
    //
    0.56
    <unused63>
    0.52
    //
    0.51
    	
    0.49
    HOC
    0.49
    tagHelperRunner
    0.48
     ballerina
    0.47
    Activations Density 0.023%

    No Known Activations