© 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. 7731
    Prev
    Next
    INDEX
    Explanations

    terms related to chemical properties and reactions of catalysts, particularly resistance to oxidation and stability

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

    phrases describing properties of resilience, stability, or tolerance in scientific contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    words describing stability, robustness, and resistance to degradation or damage.

    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
    tagext
    -0.42
    ScopeManager
    -0.41
    nodoc
    -0.36
    ulx
    -0.33
    SerialPort
    -0.33
    adpleegd
    -0.32
    tagHelper
    -0.31
     çat
    -0.31
    roleum
    -0.30
    araoh
    -0.30
    POSITIVE LOGITS
     resilient
    1.96
     resistant
    1.94
     resilience
    1.90
     withstand
    1.89
     resiliency
    1.74
     odol
    1.73
     resist
    1.66
     Resistant
    1.66
     resistentes
    1.65
     résist
    1.64
    Activations Density 1.107%

    No Known Activations