© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 64198
    Prev
    Next
    INDEX
    Explanations

    terms related to examinations and academic assessments

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

    exam, exams, examination, examining

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     câte
    -0.57
    atelli
    -0.54
    subpackage
    -0.52
     Coolidge
    -0.52
     voedsel
    -0.51
     Gutes
    -0.50
     bürger
    -0.49
     стороне
    -0.49
    atti
    -0.48
    arlı
    -0.48
    POSITIVE LOGITS
     Exam
    1.11
    Exam
    1.11
     exam
    1.11
     exams
    1.00
    exam
    0.98
     EXAM
    0.97
     Exams
    0.97
    Exams
    0.81
     examinations
    0.80
     Examination
    0.80
    Activations Density 0.005%

    No Known Activations