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. 4946
    Prev
    Next
    INDEX
    Explanations

    code snippets that manipulate data structures such as arrays and maps

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

    PHP array and code syntax

    np_acts-logits-general · gemini-2.0-flash

    code syntax parsing

    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
    ({})
    -0.57
     {}
    -0.52
    انيف
    -0.51
    GEBURTSDATUM
    -0.49
     {};
    
    -0.47
     {};
    -0.46
    {}
    -0.45
     {}),
    -0.44
    {}/
    -0.43
     instanceof
    -0.43
    POSITIVE LOGITS
    ilities
    0.68
     оригіналу
    0.65
     Roskov
    0.65
    amentals
    0.64
     array
    0.63
    MENAFN
    0.63
    assis
    0.61
     BitmapFactory
    0.61
     Moors
    0.60
    mtable
    0.60
    Activations Density 0.099%

    No Known Activations