© 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 - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 11909
    Prev
    Next
    INDEX
    Explanations

    technical configuration parameters commonly used in coding or software contexts

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

    configuration parameters and their assigned values in code or configuration files.

    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
     للاسماء
    -0.49
     autorytatywna
    -0.39
     newState
    -0.36
    SourceChecksum
    -0.35
     currentState
    -0.34
     majd
    -0.34
    feuer
    -0.33
    ItemBackground
    -0.32
    hoeddwyd
    -0.31
    进入了
    -0.31
    POSITIVE LOGITS
     threshold
    0.95
     maximum
    0.90
     minimum
    0.88
     tolerance
    0.88
     max
    0.80
     size
    0.78
     spacing
    0.77
     radius
    0.77
     thresholds
    0.76
     cutoff
    0.76
    Activations Density 1.061%

    No Known Activations