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. 1494
    Prev
    Next
    INDEX
    Explanations

    numeric representations and special characters in the text

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

    The number 2 followed by another number

    np_acts-logits-general · gemini-2.0-flash

    numbers preceded by specific characters

    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
     autorytatywna
    -0.68
    ']))
    
    -0.67
     lạc
    -0.67
    %)$
    -0.65
    */),
    -0.65
    />";
    -0.65
     Werth
    -0.64
    entrion
    -0.64
    ']],
    -0.64
     ComVisible
    -0.64
    POSITIVE LOGITS
    nd
    1.29
    2
    1.15
    0
    1.01
     thirds
    0.86
    5
    0.85
    4
    0.82
    3
    0.81
    thirds
    0.76
    1
    0.70
     nd
    0.68
    Activations Density 1.440%

    No Known Activations