© 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. 15-GEMMASCOPE-RES-16K
    11. 9371
    Prev
    Next
    INDEX
    Explanations

    references to rows and data management within structured datasets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Anhalt
    -0.87
    */),
    -0.86
     majeur
    -0.86
    Datuak
    -0.85
     virtù
    -0.81
    #+#
    -0.80
    enumii
    -0.79
     Réponses
    -0.78
    ))->
    -0.77
    aarrggbb
    -0.77
    POSITIVE LOGITS
     row
    1.56
     Row
    1.53
     rows
    1.47
     ROW
    1.39
    Row
    1.35
    row
    1.34
    rows
    1.25
     Rows
    1.24
     Rowland
    1.22
    ROW
    1.20
    Activations Density 0.049%

    No Known Activations