© 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. 4441
    Prev
    Next
    INDEX
    Explanations

    actions and events related to attempts and experiences

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

    phrases involving duration or progression, like "after [time period]" or "after [verb]ing".

    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
    RenderAtEndOf
    -0.55
    SequentialGroup
    -0.54
    adaptiveStyles
    -0.54
    ParallelGroup
    -0.51
    usercontent
    -0.50
     kasarigan
    -0.50
     становника
    -0.50
     transfieras
    -0.47
    awaiter
    -0.47
     arşivlendi
    -0.46
    POSITIVE LOGITS
    After
    0.69
     After
    0.69
     Depois
    0.66
     Após
    0.64
     وبعد
    0.63
    Depois
    0.61
     Nachdem
    0.60
    Después
    0.59
    Nachdem
    0.59
     nachdem
    0.58
    Activations Density 0.189%

    No Known Activations