© 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. 1-GEMMASCOPE-RES-16K
    11. 3673
    Prev
    Next
    INDEX
    Explanations

    the keyword "split" along with variations of the term related to dividing or separating data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    */].
    -0.63
    esinde
    -0.53
    )}</
    -0.52
    ',$
    -0.52
     tebal
    -0.50
    ’.”
    -0.49
    hod
    -0.49
    ائج
    -0.48
    براير
    -0.48
    ченко
    -0.48
    POSITIVE LOGITS
    split
    4.50
     split
    4.25
    Split
    4.01
     Split
    4.00
     splits
    3.39
     splitting
    3.33
    SPLIT
    3.17
    splitting
    2.93
    splits
    2.84
    plit
    2.60
    Activations Density 0.057%

    No Known Activations