© 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. 14-GEMMASCOPE-RES-16K
    11. 3681
    Prev
    Next
    INDEX
    Explanations

    URLs and related web content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    parsedMessage
    -1.02
     Wallflower
    -0.96
     @"/
    -0.93
    WireFormat
    -0.92
     eil
    -0.89
     Reinhold
    -0.85
     Mure
    -0.82
    (&:
    -0.81
    Gua
    -0.80
     Leipzig
    -0.77
    POSITIVE LOGITS
     https
    0.88
    Https
    0.86
     HTTPS
    0.82
    HTTPS
    0.81
    https
    0.78
    ificance
    0.77
    ttps
    0.73
     Lakeside
    0.72
    wikidata
    0.68
     Nuss
    0.66
    Activations Density 0.091%

    No Known Activations