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. 9351
    Prev
    Next
    INDEX
    Explanations

    code-related terminology and function calls in programming contexts

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

    Code related to field numbers and storage

    np_acts-logits-general · gemini-2.0-flash

    field number 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
    çoivent
    -0.53
     levure
    -0.53
     piú
    -0.50
    Since
    -0.47
     بيها
    -0.44
    cepat
    -0.43
     gibi
    -0.43
     amarillas
    -0.43
     acela
    -0.43
    Two
    -0.42
    POSITIVE LOGITS
    '),
    
    1.02
    '},
    
    1.02
     Signalez
    1.01
    ")));
    
    1.00
    '],
    
    0.97
    '));
    
    0.92
    %"),
    0.91
    tvguidetime
    0.90
    "},
    
    0.90
    Autoritní
    0.89
    Activations Density 0.133%

    No Known Activations