© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 10591
    Prev
    Next
    INDEX
    Explanations

    actions and concepts related to splitting, dividing, and decomposing elements or data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CURIAM
    -0.52
    tioners
    -0.52
    ậy
    -0.52
     referenties
    -0.51
    fır
    -0.48
     mouseY
    -0.48
     követ
    -0.48
     defStyle
    -0.48
    Referencies
    -0.48
     Atkins
    -0.47
    POSITIVE LOGITS
     splits
    1.11
     split
    1.08
     partition
    1.03
     Partition
    1.03
     splitting
    1.03
     breakup
    1.02
     Split
    1.01
     divides
    1.01
     partitioned
    0.99
    Split
    0.97
    Activations Density 0.482%

    No Known Activations