© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 608
    Prev
    Next
    INDEX
    Explanations

    references to mathematical concepts and terminology in scientific literature

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

    "Math", "Mod", and physics journals/publications

    np_acts-logits-general · gemini-2.0-flash

    Rev. Mod. Phys

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     proyección
    -0.48
     você
    -0.46
     croire
    -0.46
     getLogin
    -0.46
    kapnya
    -0.46
     cerah
    -0.45
     configuración
    -0.45
     bahía
    -0.44
     bañera
    -0.44
     calcetines
    -0.43
    POSITIVE LOGITS
     M
    0.90
     m
    0.81
    M
    0.72
    mybatisplus
    0.70
     MH
    0.69
    m
    0.68
     MC
    0.68
     MU
    0.67
     Mayhem
    0.67
     М
    0.66
    Activations Density 3.412%

    No Known Activations