© 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-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 252
    Prev
    Next
    INDEX
    Explanations

    references to educational qualifications and backgrounds

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

    Education or graduation levels

    np_acts-logits-general · gemini-2.0-flash

    degree, education, graduated

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cref
    -0.61
     Signalez
    -0.59
     deportivas
    -0.57
     cardiaque
    -0.56
     leçon
    -0.54
     présentes
    -0.54
    stø
    -0.54
     étoient
    -0.53
    vivencia
    -0.53
     leçons
    -0.52
    POSITIVE LOGITS
     graduate
    1.45
     graduated
    1.37
     college
    1.29
     graduates
    1.26
     degree
    1.25
     educated
    1.24
     Bachelor
    1.23
     graduating
    1.21
     degrees
    1.18
     education
    1.18
    Activations Density 0.267%

    No Known Activations