© 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. 1-GEMMASCOPE-RES-16K
    6. 2060
    Prev
    Next
    INDEX
    Explanations

    instances of the word "graduated" and its variations, indicating a focus on educational achievements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    affaire
    -0.39
     provas
    -0.38
    exitRule
    -0.34
     censura
    -0.34
    NSNotification
    -0.34
    rzost
    -0.33
     semula
    -0.33
     vendas
    -0.33
     taxas
    -0.33
     rotina
    -0.33
    POSITIVE LOGITS
     graduated
    1.05
     gradient
    0.85
     graduating
    0.84
     graduation
    0.81
    gradu
    0.77
     Gradient
    0.76
     grad
    0.75
     gradu
    0.74
     passage
    0.73
     forgotten
    0.72
    Activations Density 0.261%

    No Known Activations