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

    Neuronpedia

    Jacobian LensNEW
    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. 21-GEMMASCOPE-RES-16K
    11. 13113
    Prev
    Next
    INDEX
    Explanations

    programming-related terms and constructs in code snippets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SequentialGroup
    -0.50
    IntoConstraints
    -0.49
    webElementXpaths
    -0.47
    
    -0.46
    XmlAccessType
    -0.42
     gonzález
    -0.40
     fallu
    -0.37
    styleType
    -0.36
    ksikon
    -0.36
    abestanden
    -0.35
    POSITIVE LOGITS
     random
    1.27
     randomly
    1.19
     Random
    1.09
    random
    1.08
    Random
    1.03
    随机
    0.97
     randomization
    0.96
     RANDOM
    0.95
     randomness
    0.93
     randomized
    0.90
    Activations Density 0.572%

    No Known Activations