© 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. 10643
    Prev
    Next
    INDEX
    Explanations

    historical mentions of inventions and their inventors

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

    dates and years when something was invented or first occurred.

    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
     ees
    -0.41
     <<<<<<<<<<<<<<
    -0.41
    ScopeManager
    -0.40
     Roskov
    -0.39
     kasarigan
    -0.37
     BoxFit
    -0.35
    ngdoc
    -0.35
    ardless
    -0.35
    arent
    -0.34
    eter
    -0.33
    POSITIVE LOGITS
     first
    1.95
     pertama
    1.55
    first
    1.50
     originally
    1.49
     впервые
    1.48
     primero
    1.36
     firft
    1.35
     primeira
    1.34
     eerste
    1.32
     erstmals
    1.29
    Activations Density 1.195%

    No Known Activations