© 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. 31-GEMMASCOPE-RES-16K
    6. 11391
    Prev
    Next
    INDEX
    Explanations

    elements related to user interface components in coding, particularly buttons and form inputs

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

    HTML and code markup syntax elements like buttons, input fields, and form attributes.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rhestr
    -0.59
    ########.
    -0.47
    
    -0.41
    occuper
    -0.41
     مرئيه
    -0.40
    Переваги
    -0.39
    elemField
    -0.39
     appartements
    -0.38
     wpis
    -0.36
    PackageInfo
    -0.36
    POSITIVE LOGITS
     button
    2.06
     buttons
    1.96
    button
    1.73
     Button
    1.70
     Buttons
    1.63
    Button
    1.62
     BUTTON
    1.61
    按钮
    1.59
    ボタン
    1.55
     버튼
    1.53
    Activations Density 0.295%

    No Known Activations