© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 12569
    Prev
    Next
    INDEX
    Explanations

    user interactions involving clicking and pressing buttons

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

    associated with buttons or clicks

    np_acts-logits-general · gemini-2.0-flash

    button click

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/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.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     يتيمه
    -0.48
     rhestr
    -0.47
    elemField
    -0.46
     ContentValues
    -0.44
    MENAFN
    -0.42
     kasarigan
    -0.39
    localctx
    -0.35
    RetentionPolicy
    -0.34
    ########.
    -0.34
    Transcripción
    -0.34
    POSITIVE LOGITS
     buttons
    1.28
     button
    1.27
     Button
    1.09
    button
    1.08
    Button
    1.07
     Buttons
    1.05
    JButton
    0.98
     botón
    0.98
    buttons
    0.98
     tombol
    0.95
    Activations Density 0.395%

    No Known Activations