© 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. 4486
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to programming and data structures

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

    sequences describing procedural steps where actions are performed in a specific order.

    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
    
    -0.43
    rungsseite
    -0.43
    !*\
    -0.41
    værende
    -0.35
     avoient
    -0.35
    ngdoc
    -0.35
    おり
    -0.34
    ljiv
    -0.34
    Tembelea
    -0.33
    iocene
    -0.32
    POSITIVE LOGITS
     then
    4.22
     Then
    3.14
    Then
    3.11
    then
    3.08
     THEN
    2.83
     dann
    2.81
     entonces
    2.78
     então
    2.69
     سپس
    2.67
     kemudian
    2.66
    Activations Density 3.690%

    No Known Activations