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. 20-GEMMASCOPE-RES-16K
    6. 5223
    Prev
    Next
    INDEX
    Explanations

    elements related to code structuring and definitions in programming syntax

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

    Code tokens followed by semicolons

    np_acts-logits-general · gemini-2.0-flash

    ending statements with `;`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ""
    
    -0.92
    __':
    
    -0.89
    !")
    
    -0.86
    =[]
    
    -0.86
     []
    
    -0.81
     "")
    
    -0.80
    ++
    
    -0.79
    ")
    
    -0.77
     ''
    
    -0.74
    "):
    
    -0.74
    POSITIVE LOGITS
    ;
    2.79
    ';
    2.27
    ";
    2.20
    ”;
    2.20
    »;
    2.16
    ’;
    2.16
    ();
    2.14
    ;
    2.14
    .;
    2.12
    $;
    2.11
    Activations Density 2.354%

    No Known Activations