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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 9719
    Prev
    Next
    INDEX
    Explanations

    references to educational settings, particularly related to grade levels and school structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     teenagers
    -0.85
     college
    -0.84
     teenage
    -0.81
    高校生
    -0.79
     teen
    -0.79
     teens
    -0.77
     colleges
    -0.77
     Teen
    -0.75
    高校
    -0.73
    Teen
    -0.72
    POSITIVE LOGITS
     Primary
    0.60
     primaria
    0.59
     primaire
    0.55
     recess
    0.54
     primary
    0.54
    primary
    0.53
    Primary
    0.52
     maît
    0.52
     PRIMARY
    0.47
     elementary
    0.46
    Activations Density 0.139%

    No Known Activations