Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 2281
    Prev
    Next
    INDEX
    Explanations

    instances of the word "split" in various contexts related to programming, particularly in string manipulation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Administrativna
    -0.73
     الرياضيه
    -0.72
     препратки
    -0.62
    PhysRevD
    -0.61
     hemlock
    -0.58
     ModelExpression
    -0.57
     referrerpolicy
    -0.57
     Sarm
    -0.55
    براير
    -0.54
     Huntingdon
    -0.54
    POSITIVE LOGITS
    split
    1.96
    Split
    1.55
     split
    1.50
     Split
    1.45
    SPLIT
    1.28
     splits
    1.21
    plit
    1.14
     StringTokenizer
    1.11
     splitting
    1.07
    splits
    1.02
    Activations Density 0.019%

    No Known Activations