© 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. 19-GEMMASCOPE-RES-16K
    6. 16156
    Prev
    Next
    INDEX
    Explanations

    references to specific programming elements and structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     propOrder
    -0.56
     consultato
    -0.51
    AutoScaleMode
    -0.50
    onez
    -0.48
     réservé
    -0.46
    rogels
    -0.46
    ocardium
    -0.45
     OBITUARY
    -0.43
    sterreich
    -0.43
    tauan
    -0.43
    POSITIVE LOGITS
     LoggerFactory
    0.84
     Italijani
    0.76
     متعلقه
    0.75
     Hift
    0.73
     Савезне
    0.73
    })*/
    0.72
     Theſe
    0.68
     Efq
    0.66
     GetEnumerator
    0.66
     Diſ
    0.63
    Activations Density 0.674%

    No Known Activations