© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 1162
    Prev
    Next
    INDEX
    Explanations

    references to inventions and innovations, especially in technical or scientific contexts

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

    patent document headers that include the phrase "Field of the Invention" and related text.

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

    patent document headers and the beginning of patent claim sections.

    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
    quelize
    -0.35
    
    -0.34
    PDOException
    -0.32
     oprot
    -0.31
    拭
    -0.30
    ModelState
    -0.30
    aurait
    -0.29
    apimachinery
    -0.29
    willi
    -0.28
    badlogic
    -0.28
    POSITIVE LOGITS
     relates
    1.65
     pertains
    1.60
     pertain
    1.52
     relate
    1.50
     riguarda
    1.47
     dotyczy
    1.45
     concerne
    1.42
     riguard
    1.37
     concern
    1.34
     concerns
    1.33
    Activations Density 1.224%

    No Known Activations