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

    Neuronpedia

    APICircuit 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. 2067
    Prev
    Next
    INDEX
    Explanations

    references to regular expressions and validation of input

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     '>=
    -0.64
    CONCURRENT
    -0.61
     {},
    
    -0.60
    "]);
    
    -0.60
    >");
    
    -0.59
     '*')
    -0.58
    ()]);
    -0.58
     "-";
    -0.58
     ""));
    -0.57
    strix
    -0.57
    POSITIVE LOGITS
     characters
    0.81
     character
    0.78
     escape
    0.70
     Characters
    0.70
     Escape
    0.69
     terminator
    0.65
     escaping
    0.63
     escaped
    0.63
     Character
    0.63
    Escape
    0.62
    Activations Density 0.691%

    No Known Activations