© 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. 5-GEMMASCOPE-RES-16K
    6. 6705
    Prev
    Next
    INDEX
    Explanations

    specific statistical comparisons, particularly in the context of algorithms or data analysis

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

    conditional phrases and expressions related to comparisons and evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     
    -0.42
     The
    -0.41
     He
    -0.41
     couvert
    -0.41
     per
    -0.40
    nya
    -0.40
    nare
    -0.40
    Autores
    -0.39
    時点
    -0.39
     Ca
    -0.39
    POSITIVE LOGITS
     GetEnumerator
    0.90
     EconPapers
    0.90
    MeasureSpec
    0.83
    出版年
    0.80
     estekak
    0.78
    Datuak
    0.77
    GEBURTSDATUM
    0.74
     समीक्षक
    0.73
    bootstrapcdn
    0.71
    ]-->
    0.70
    Activations Density 1.463%

    No Known Activations