© 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. 534
    Prev
    Next
    INDEX
    Explanations

    references to user privacy and data management practices

    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
     Be
    -0.79
    Go
    -0.79
    Com
    -0.79
    Be
    -0.78
     Go
    -0.78
    Play
    -0.77
    End
    -0.74
    Do
    -0.73
    Have
    -0.72
    Work
    -0.72
    POSITIVE LOGITS
     Wrist
    0.83
     Wreath
    0.80
     Cassette
    0.77
     Gown
    0.77
    Autoritní
    0.77
     Stretcher
    0.75
     Necklace
    0.75
     Hashtag
    0.74
     Histogram
    0.74
     Trajectory
    0.74
    Activations Density 1.199%

    No Known Activations