© 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. 34-GEMMASCOPE-RES-16K
    6. 11488
    Prev
    Next
    INDEX
    Explanations

    terms related to research ethics and approval processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/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.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    blurRadius
    -0.45
     FontFamily
    -0.40
    MLLoader
    -0.39
     behoort
    -0.34
    czywiście
    -0.34
     Савезне
    -0.34
    DebuggerNonUser
    -0.32
     Biôgrafia
    -0.32
     quanto
    -0.31
     fometimes
    -0.31
    POSITIVE LOGITS
     initComponents
    0.74
     nakalista
    0.69
    MessageOf
    0.68
    +#+#
    0.67
    Autoritní
    0.62
     overview
    0.61
     Considerations
    0.60
     autorytatywna
    0.57
     considerations
    0.57
     Details
    0.57
    Activations Density 0.551%

    No Known Activations