© 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. 20-GEMMASCOPE-RES-16K
    6. 3608
    Prev
    Next
    INDEX
    Explanations

    CSS margin and padding properties

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

    CSS and HTML layout properties, specifically margin, position, and layout attributes.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    دانشنامهٔ
    -0.56
    webElementGuid
    -0.55
    RTEX
    -0.55
    IsContent
    -0.50
    tinyos
    -0.48
     TextInputType
    -0.48
    ьажоргаш
    -0.46
    Transkript
    -0.46
    ValueStyle
    -0.46
    
    
    -0.46
    POSITIVE LOGITS
    marginRight
    0.49
    SizedBox
    0.45
    marginBottom
    0.41
     oprot
    0.41
     differences
    0.39
     liền
    0.38
     rápidamente
    0.38
     unsightly
    0.37
     marginBottom
    0.37
    ądze
    0.37
    Activations Density 0.102%

    No Known Activations