© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 16-GEMMASCOPE-RES-65K
    11. 27351
    Prev
    Next
    INDEX
    Explanations

    instances of the keyword "typeof" used in a programming context

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

    typeof followed by parenthesis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    borderSide
    -0.82
     nakalista
    -0.77
    makeConstraints
    -0.77
     invokingState
    -0.73
     unknownFields
    -0.73
     createSlice
    -0.71
    FilterChain
    -0.70
    rawDesc
    -0.68
     RST
    -0.67
    UVWXYZ
    -0.67
    POSITIVE LOGITS
    typeof
    1.05
     typeof
    0.94
     disponibilités
    0.91
     ujednoznacz
    0.66
    tschaft
    0.62
    氓
    0.60
     MonoBehaviour
    0.57
    bishop
    0.57
    onomía
    0.56
    似
    0.56
    Activations Density 0.004%

    No Known Activations