© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 105878
    Prev
    Next
    INDEX
    Explanations

    sections of code or comments that indicate organizational structure or setup in a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.57
     ویکی‌پدی
    -0.55
    pushFollow
    -0.47
    richTextPanel
    -0.46
    ksikon
    -0.45
    しゃれ
    -0.42
    AnimationsModule
    -0.42
    Controllo
    -0.41
     exercí
    -0.41
    ंदीखरीदारी
    -0.41
    POSITIVE LOGITS
    참고
    0.62
    \{\\
    0.53
    @[+][
    0.50
     صوتيه
    0.48
     reserv
    0.48
    fferty
    0.47
    AutoField
    0.46
     religious
    0.46
     ③
    0.46
     '
    0.46
    Activations Density 0.015%

    No Known Activations