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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 8091
    Prev
    Next
    INDEX
    Explanations

    information related to graduation events and high school students

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

    Mention of being alumni or graduates

    np_acts-logits-general · gemini-2.0-flash

    graduating class affiliation

    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
     AssemblyTitle
    -0.88
    DeleteBehavior
    -0.74
    styleType
    -0.73
    }))
    
    -0.72
    Tembelea
    -0.72
    featureID
    -0.70
    endphp
    -0.68
     متعلقه
    -0.68
    Rohy
    -0.66
    abestanden
    -0.65
    POSITIVE LOGITS
     class
    1.62
     graduates
    1.60
     graduating
    1.59
     Class
    1.59
    Class
    1.48
    class
    1.42
     graduated
    1.37
     Graduates
    1.32
     graduate
    1.26
     CLASS
    1.25
    Activations Density 0.160%

    No Known Activations