© 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. 15-GEMMASCOPE-RES-16K
    6. 1665
    Prev
    Next
    INDEX
    Explanations

    actions and event handlers related to button clicks and user interactions in the code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    endpush
    -0.51
     sumpay
    -0.51
    NameInMap
    -0.46
     ostavi
    -0.45
     sürd
    -0.43
     gravy
    -0.43
    Tikang
    -0.43
     eşofman
    -0.43
     silks
    -0.43
     chimneys
    -0.42
    POSITIVE LOGITS
    OnClickListener
    1.09
     onClick
    1.05
    onClick
    0.92
    onclick
    0.90
     actionPerformed
    0.86
     onclick
    0.85
    UpInside
    0.80
    click
    0.78
    Click
    0.77
     click
    0.75
    Activations Density 0.062%

    No Known Activations