© 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. 5398
    Prev
    Next
    INDEX
    Explanations

    elements related to unique transformations or adaptations

    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
    IsContent
    -0.87
    
    -0.72
    oa̍t
    -0.67
    ValueStyle
    -0.66
    Jegyzetek
    -0.66
    UnusedPrivate
    -0.64
    évaluateur
    -0.62
    Aholisi
    -0.61
     kasarigan
    -0.61
     للاسماء
    -0.60
    POSITIVE LOGITS
    moiselle
    0.62
     anteriormente
    0.58
     حديث
    0.58
     thereon
    0.56
    enseits
    0.56
    bene
    0.56
     herein
    0.56
    cbd
    0.55
     herewith
    0.55
     hereto
    0.55
    Activations Density 0.657%

    No Known Activations