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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 9630
    Prev
    Next
    INDEX
    Explanations

    code that includes or refers to various header files and libraries in programming

    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
    Портал
    -0.75
    Portale
    -0.75
     صوتيه
    -0.74
     TextAlign
    -0.71
    principalColumn
    -0.71
    بوابة
    -0.69
     ""],
    -0.67
     onAnimation
    -0.67
    تقاوى
    -0.67
     оригіналу
    -0.65
    POSITIVE LOGITS
    ↵
    0.68
    ↵↵↵
    0.57
     kveld
    0.46
    iostream
    0.45
    enumi
    0.44
    ↵↵↵↵
    0.44
     estekak
    0.43
    >
    
    0.42
    pyrid
    0.42
    ↵↵
    0.42
    Activations Density 0.047%

    No Known Activations