© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 40-GEMMASCOPE-RES-16K
    11. 2132
    Prev
    Next
    INDEX
    Explanations

    syntax elements and attributes commonly used in XML and HTML code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     COVID
    -0.65
     pandemia
    -0.64
     Covid
    -0.62
    COVID
    -0.62
     🤷
    -0.59
     covid
    -0.57
    contentLoaded
    -0.56
     Pandemie
    -0.56
     pandemic
    -0.56
    personality
    -0.54
    POSITIVE LOGITS
    http
    2.42
     http
    2.38
    Http
    1.40
     Http
    1.27
     HTTP
    1.17
    ttp
    1.15
    HTTP
    1.09
     htt
    0.92
    htt
    0.81
    httpd
    0.73
    Activations Density 0.388%

    No Known Activations