© 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. 18-GEMMASCOPE-RES-16K
    11. 4394
    Prev
    Next
    INDEX
    Explanations

    references to data types related to byte arrays and their manipulation

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

    "byte" or "bytes" tokens

    np_acts-logits-general · gemini-2.0-flash

    byte array

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    (!__
    -0.90
    rungsseite
    -0.89
    RUnlock
    -0.87
    onOptions
    -0.77
    awarkan
    -0.75
    LEGGI
    -0.75
    modelBuilder
    -0.74
     &___
    -0.73
    GEBURTSDATUM
    -0.72
    SBATCH
    -0.70
    POSITIVE LOGITS
    bytes
    1.03
     bytes
    0.98
    BYTES
    0.89
    Bytes
    0.89
     byte
    0.89
     Byte
    0.85
     Bytes
    0.85
    Byte
    0.83
     BYTE
    0.79
    byte
    0.71
    Activations Density 0.180%

    No Known Activations