© 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. 25-GEMMASCOPE-RES-16K
    11. 1648
    Prev
    Next
    INDEX
    Explanations

    programming-related terminology and syntax elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Hennessy
    -0.76
    ExtendWith
    -0.73
     Magdalen
    -0.72
     Bowen
    -0.69
     Rodin
    -0.67
     Landis
    -0.66
     Burma
    -0.66
     Krakow
    -0.66
     Lorena
    -0.65
     Jacinto
    -0.64
    POSITIVE LOGITS
     Klee
    0.89
     Garr
    0.78
     Colbert
    0.74
     Ebert
    0.73
     Papi
    0.73
     Caldwell
    0.72
     Frie
    0.72
     Pene
    0.71
     Sando
    0.70
     Arora
    0.70
    Activations Density 1.665%

    No Known Activations