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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 19-GEMMASCOPE-RES-16K
    11. 15916
    Prev
    Next
    INDEX
    Explanations

    instances of the word "split" and its variations, as well as concepts surrounding division or separation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wpdb
    -0.52
     CURIAM
    -0.48
    fromnode
    -0.47
    (".");
    -0.47
    </h6>
    -0.47
    ècie
    -0.46
    IORS
    -0.45
    itemView
    -0.45
    дь
    -0.44
    Économie
    -0.43
    POSITIVE LOGITS
     split
    1.05
     Split
    1.04
    SPLIT
    1.02
    split
    1.01
    splits
    1.00
    Split
    0.98
     splits
    0.97
     splitting
    0.89
    plit
    0.88
    splitting
    0.88
    Activations Density 0.087%

    No Known Activations