© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 15551
    Prev
    Next
    INDEX
    Explanations

    procedures and descriptions related to laboratory experiments and sample processing

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

    laboratory equipment and containers, particularly test tubes and vessels used in scientific experiments.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.61
    awaiter
    -0.59
    tagHelperRunner
    -0.55
    UrlResolution
    -0.54
     AssemblyCulture
    -0.54
    queryInterface
    -0.53
    /**
    -0.53
    ebaran
    -0.52
    richTextPanel
    -0.52
    jsonwebtoken
    -0.51
    POSITIVE LOGITS
    pperware
    0.44
    enderror
    0.38
     working
    0.36
    ListActivity
    0.33
     lined
    0.33
    writeHead
    0.33
     createSprite
    0.32
     ๆ
    0.32
     contin
    0.31
     meeting
    0.31
    Activations Density 0.224%

    No Known Activations