© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 103513
    Prev
    Next
    INDEX
    Explanations

    coding constructs related to array handling and checking for array types

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     flagship
    -0.42
    CheckedChanged
    -0.40
     never
    -0.38
     pumped
    -0.37
     hopefully
    -0.37
     protected
    -0.36
     Aba
    -0.36
    detectChanges
    -0.35
    nextProps
    -0.35
    NotBlank
    -0.34
    POSITIVE LOGITS
    GOTREF
    0.84
    Personendaten
    0.75
    isArray
    0.73
     Мексичка
    0.71
     الحره
    0.61
     Chwiliwch
    0.60
    XmlAccessType
    0.59
    MigrationBuilder
    0.58
    NameInMap
    0.58
    principalColumn
    0.58
    Activations Density 0.006%

    No Known Activations