© 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. 9-GEMMASCOPE-RES-16K
    11. 164
    Prev
    Next
    INDEX
    Explanations

    operations involving the word "split" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/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.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     resourceCulture
    -0.87
    cshtml
    -0.77
    contentValues
    -0.75
     élevés
    -0.72
     soldati
    -0.72
     DMX
    -0.72
    mbres
    -0.71
     Glaser
    -0.71
    ädigung
    -0.71
    судар
    -0.71
    POSITIVE LOGITS
    split
    1.44
     split
    1.36
     Split
    1.35
    Split
    1.32
     splits
    1.26
    SPLIT
    1.25
    splits
    1.18
    plit
    1.17
     splitting
    1.02
    Splits
    0.97
    Activations Density 0.042%

    No Known Activations