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. 3-GEMMASCOPE-RES-16K
    6. 6125
    Prev
    Next
    INDEX
    Explanations

    references to time, specifically focusing on the previous year

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    leges
    -0.51
    //
    -0.45
    ची
    -0.42
     vira
    -0.41
    hape
    -0.39
    ळ
    -0.38
    DoubleQuotes
    -0.38
     sizeof
    -0.37
    inem
    -0.37
    Bonnie
    -0.37
    POSITIVE LOGITS
    mybatisplus
    0.94
     ExecuteAsync
    0.89
    __':
    
    0.87
     initComponents
    0.84
     typelib
    0.78
    Gemeinden
    0.75
    HtmlAttribute
    0.74
    kuuta
    0.74
     endwhile
    0.73
    expandindo
    0.73
    Activations Density 0.177%

    No Known Activations