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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 3645
    Prev
    Next
    INDEX
    Explanations

    mentions of educational courses and degrees

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

    terms related to education, degrees, and educational institutions.

    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
     секу
    -0.38
    exels
    -0.38
    codegen
    -0.37
     مرئيه
    -0.36
    LookAnd
    -0.36
    msgSender
    -0.36
    ejs
    -0.35
    Cringe
    -0.34
    اتها
    -0.34
    raught
    -0.34
    POSITIVE LOGITS
     enrolled
    0.57
     enrolling
    0.57
     enrollment
    0.56
     enrolment
    0.51
     courses
    0.51
    Enrollment
    0.51
    Courses
    0.50
     Learners
    0.50
     enroll
    0.49
     learning
    0.48
    Activations Density 0.065%

    No Known Activations