© 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. 15-GEMMASCOPE-RES-16K
    6. 3310
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to graphs and graphical data representation

    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
    PendingIntent
    -0.94
    venido
    -0.87
    tableFuture
    -0.83
    devise
    -0.81
    +#+#
    -0.79
    abcdefghijklmnop
    -0.78
     Squal
    -0.77
    awaiter
    -0.75
    IBarButtonItem
    -0.75
    ]),
    
    -0.75
    POSITIVE LOGITS
     graphs
    1.31
     graph
    1.19
     Graph
    1.16
    Graphs
    1.09
    Graph
    1.07
     GRAPH
    1.04
    graph
    1.01
    GRAPH
    1.01
     Graphs
    1.00
    ograph
    0.98
    Activations Density 0.156%

    No Known Activations