© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 2317
    Prev
    Next
    INDEX
    Explanations

    occurrences of enumerations in a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     convin
    -0.63
    حياته
    -0.62
     Samaria
    -0.60
     Schick
    -0.59
    oustic
    -0.57
    vastava
    -0.56
     interess
    -0.56
    iddhartha
    -0.56
    RTLE
    -0.56
     skry
    -0.55
    POSITIVE LOGITS
     enum
    2.74
    enum
    2.63
    Enum
    2.58
     Enum
    2.58
    ENUM
    2.07
     enums
    2.06
    enums
    1.74
    Enums
    1.63
     enumeration
    1.57
    Enumerated
    1.53
    Activations Density 0.048%

    No Known Activations