© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 36-GEMMASCOPE-RES-16K
    6. 16371
    Prev
    Next
    INDEX
    Explanations

    technical terms and identifiers related to networking protocols and programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     still
    -0.42
     LeBlanc
    -0.41
    still
    -0.40
     dennoch
    -0.38
     Display
    -0.38
    ople
    -0.38
    ode
    -0.37
     Bischof
    -0.37
     тех
    -0.36
     बि
    -0.35
    POSITIVE LOGITS
     autorytatywna
    0.69
    IUrlHelper
    0.67
    httphttps
    0.58
    RTGC
    0.56
    
    0.55
    tagHelperRunner
    0.53
     ویکی‌پدی
    0.53
    ніципа
    0.52
    RTEX
    0.52
    Tikang
    0.49
    Activations Density 0.435%

    No Known Activations