© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 8997
    Prev
    Next
    INDEX
    Explanations

    phrases indicating educational achievements and graduation

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

    graduation or being qualified

    np_acts-logits-general · gemini-2.0-flash

    graduated from

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
     propOrder
    -0.46
    textLabel
    -0.37
     bits
    -0.37
    LookAnd
    -0.37
     Redskins
    -0.37
     MotionEvent
    -0.37
    eschön
    -0.37
     pin
    -0.37
    Belgique
    -0.37
     ThemeData
    -0.36
    POSITIVE LOGITS
     graduation
    1.05
     graduate
    1.05
    Graduation
    1.00
     GRADUATE
    0.99
     graduating
    0.97
     Graduate
    0.95
     Graduation
    0.95
    Graduate
    0.94
     Graduates
    0.94
     graduates
    0.93
    Activations Density 0.189%

    No Known Activations