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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 7043
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word 'graduate' and its variations indicating educational achievements

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

    statements about graduating from a university or academic achievement.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    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
    LookAnd
    -0.49
     propOrder
    -0.42
     Espagne
    -0.40
     MotionEvent
    -0.39
     posX
    -0.39
    Chen
    -0.39
    key
    -0.38
    Amos
    -0.38
     Murcia
    -0.37
    thenReturn
    -0.37
    POSITIVE LOGITS
     graduate
    0.97
    Graduate
    0.94
     Graduate
    0.94
     GRADUATE
    0.94
    Graduation
    0.89
     graduation
    0.88
     graduating
    0.88
     Graduation
    0.88
     Graduates
    0.88
    graduate
    0.87
    Activations Density 0.111%

    No Known Activations