© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 8297
    Prev
    Next
    INDEX
    Explanations

    references to the action or concept of splitting or dividing

    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
    cshtml
    -0.73
    TextWatcher
    -0.72
     Tinggi
    -0.69
    tiera
    -0.69
     baterai
    -0.69
     supérieurs
    -0.68
     tinggi
    -0.68
     NGC
    -0.67
    iQ
    -0.67
    </strong>
    -0.67
    POSITIVE LOGITS
     split
    2.12
     Split
    1.99
    split
    1.97
    Split
    1.91
     splits
    1.86
    SPLIT
    1.77
    splits
    1.65
     splitting
    1.62
    plit
    1.57
    splitting
    1.52
    Activations Density 0.103%

    No Known Activations