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. 2972
    Prev
    Next
    INDEX
    Explanations

    references to genetic concepts and terminology

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

    Terms related to genetics or DNA

    np_acts-logits-general · gemini-2.0-flash

    genetic sequences and engineering

    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
    tagHelperRunner
    -0.75
    inghouse
    -0.69
    setVerticalGroup
    -0.62
    BeginContext
    -0.61
    )";
    
    -0.60
     Efq
    -0.59
    schild
    -0.59
    Amicalement
    -0.59
    _;
    
    -0.57
     />';
    -0.57
    POSITIVE LOGITS
     sequences
    0.61
     sequence
    0.56
     engineering
    0.53
     coding
    0.51
     صوتيه
    0.50
    InitVars
    0.49
     encoding
    0.49
     bank
    0.48
     material
    0.48
    CodedInputStream
    0.48
    Activations Density 0.678%

    No Known Activations