© 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. 15419
    Prev
    Next
    INDEX
    Explanations

    terms and metrics related to statistical analysis and modeling in scientific contexts

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

    scientific paper content, particularly the conclusions and summary sections in academic research papers.

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

    technical and scientific language with mathematical notation and formal academic discourse.

    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
    faßt
    -1.03
     idéia
    -1.00
     muß
    -0.96
     daß
    -0.93
     läßt
    -0.89
     Daß
    -0.84
     Miß
    -0.77
     Schluß
    -0.77
     mußten
    -0.76
     Einfluß
    -0.75
    POSITIVE LOGITS
     incentiv
    0.87
     microbiome
    0.84
     impactful
    0.84
     nuanced
    0.75
     onboarding
    0.73
     agnostic
    0.72
     curated
    0.72
     leveraging
    0.70
     showcased
    0.68
     workflows
    0.68
    Activations Density 8.966%

    No Known Activations