© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 7573
    Prev
    Next
    INDEX
    Explanations

    references to students and their experiences or roles

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

    students or a student

    np_acts-logits-general · gemini-2.0-flash

    student

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     regalías
    -0.59
     conhece
    -0.58
    convite
    -0.57
     vorige
    -0.55
    altezza
    -0.54
     metálica
    -0.54
     cenar
    -0.53
     boxeo
    -0.53
     repuesto
    -0.52
     sintética
    -0.51
    POSITIVE LOGITS
    Student
    1.89
     Student
    1.86
     student
    1.84
     Students
    1.81
    Students
    1.75
     students
    1.71
    student
    1.69
     STUDENT
    1.58
    students
    1.56
     STUDENTS
    1.49
    Activations Density 0.037%

    No Known Activations