© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 104878
    Prev
    Next
    INDEX
    Explanations

    programming terminology and constructs related to rules and symbols

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    Negative Logits
    UnusedPrivate
    -0.40
    ("'"
    -0.38
    mybatisplus
    -0.38
    ℤ
    -0.37
     snippetHide
    -0.35
    URLConnection
    -0.35
     تعدى
    -0.35
     aapt
    -0.35
     AdapterView
    -0.35
    IBOutlet
    -0.35
    POSITIVE LOGITS
    RULE
    1.03
     rule
    1.03
    rule
    1.01
     RULE
    0.99
    Rule
    0.98
     Rule
    0.93
     getRule
    0.83
    rules
    0.79
     rules
    0.79
    Rules
    0.75
    Activations Density 0.001%

    No Known Activations