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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 10-GEMMASCOPE-RES-16K
    6. 11725
    Prev
    Next
    INDEX
    Explanations

    terms related to engineering concepts and technical processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     treści
    -0.46
     papir
    -0.46
    modium
    -0.46
     trekken
    -0.45
    bietern
    -0.45
     المكتبه
    -0.43
     paper
    -0.43
     كريم
    -0.42
    ınar
    -0.42
    قديم
    -0.42
    POSITIVE LOGITS
     industrial
    1.07
     Industrial
    1.03
    industrial
    0.97
    Industrial
    0.96
     industriale
    0.94
     industriales
    0.93
     industriel
    0.92
     industriels
    0.90
     INDUSTRIAL
    0.85
     industrielle
    0.84
    Activations Density 1.035%

    No Known Activations