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. 10775
    Prev
    Next
    INDEX
    Explanations

    evidence and relationships related to health studies and community interventions

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

    "that" or a comma

    np_acts-logits-general · gemini-2.0-flash

    that followed by a word

    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
    I
    -0.77
     coisa
    -0.65
     dicen
    -0.64
    We
    -0.64
     thingy
    -0.61
     entendido
    -0.60
    You
    -0.59
    Maybe
    -0.58
    They
    -0.58
    you
    -0.57
    POSITIVE LOGITS
    )";
    
    1.19
    )");
    
    1.16
    )"),
    1.09
    "):
    
    1.07
    '},
    
    1.05
    />";
    1.04
    ")"
    1.02
    '):
    
    1.02
     the
    0.96
    $}}
    0.95
    Activations Density 1.185%

    No Known Activations