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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 2-GEMMASCOPE-RES-16K
    6. 15037
    Prev
    Next
    INDEX
    Explanations

    variations of the word "return" in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     elems
    -0.54
    badah
    -0.54
     initiative
    -0.53
    httphttps
    -0.51
    who
    -0.49
    Tembelea
    -0.49
    ोग
    -0.48
    ಿಕ
    -0.48
     CreateTagHelper
    -0.48
    indeed
    -0.47
    POSITIVE LOGITS
     Return
    1.64
    Return
    1.63
     RETURN
    1.32
     Returns
    1.31
    RETURN
    1.24
    Returns
    1.15
     return
    1.08
     返回
    1.08
     returned
    1.04
    返回
    1.03
    Activations Density 0.134%

    No Known Activations