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. 16-GEMMASCOPE-RES-16K
    6. 14897
    Prev
    Next
    INDEX
    Explanations

    instances of AJAX-related actions or errors in code context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code snippets or programming-related terms

    np_acts-logits-general · gemini-2.0-flash

    UI popups and clicks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    HomeAsUpEnabled
    -0.57
     AssemblyCulture
    -0.57
    RegressionTest
    -0.57
    出版年
    -0.57
     vacacionales
    -0.56
    enterOuterAlt
    -0.53
     vettoriale
    -0.53
    DataAnnotations
    -0.52
     FileInputStream
    -0.52
     administrativos
    -0.51
    POSITIVE LOGITS
     pop
    0.67
     popup
    0.64
     popu
    0.55
     సౌకర్య
    0.54
     Pop
    0.53
    ///
    
    0.52
     UI
    0.52
     spur
    0.49
     display
    0.49
     clicked
    0.49
    Activations Density 0.662%

    No Known Activations