© 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 - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 2994
    Prev
    Next
    INDEX
    Explanations

    code structures or syntax used in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Efq
    -0.83
     CWE
    -0.73
     AdapterView
    -0.71
    bootstrapcdn
    -0.70
     Italijani
    -0.68
     Meksiku
    -0.68
    getRuntime
    -0.66
     RIPRODUZIONE
    -0.65
     nonatomic
    -0.65
     становника
    -0.64
    POSITIVE LOGITS
    +//
    0.56
    +};
    0.50
    +
    0.48
     <<<<<<<<<<<<<<
    0.48
    +#
    0.48
    اشت
    0.46
    |+
    0.46
    Anhalt
    0.46
     dene
    0.46
    ↵↵
    0.46
    Activations Density 0.151%

    No Known Activations