Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 6025
    Prev
    Next
    INDEX
    Explanations

    numerical and demographic information related to education and personal history

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

    school or education

    np_acts-logits-general · gemini-2.0-flash

    education and student life

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Monfieur
    -0.60
     Majefty
    -0.57
     pleaſure
    -0.57
    plier
    -0.56
     myſelf
    -0.55
    ſelf
    -0.55
     raiſ
    -0.55
     snippetHide
    -0.54
     ſhe
    -0.54
     juſ
    -0.52
    POSITIVE LOGITS
     graduating
    1.02
     graduation
    1.01
     student
    0.93
     classmates
    0.89
    student
    0.88
     Graduation
    0.88
     Enrollment
    0.84
     campus
    0.82
     graduates
    0.82
     matric
    0.82
    Activations Density 0.198%

    No Known Activations