© 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. 22-GEMMASCOPE-RES-16K
    11. 5720
    Prev
    Next
    INDEX
    Explanations

    the word "Gu" and its variations, indicating a focus on references related to "Gu."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    starting with "Gu" followed by other characters

    np_acts-logits-general · gemini-2.0-flash

    Gu followed by a letter

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -0.91
     שוליים
    -0.84
    ReusableCell
    -0.70
    TagMode
    -0.69
    +#+
    -0.64
    BeginContext
    -0.61
    Chham
    -0.58
    CrossRef
    -0.58
    Odkazy
    -0.57
     समीक्षक
    -0.56
    POSITIVE LOGITS
    Gu
    0.70
     Gu
    0.63
     Gué
    0.53
    adalah
    0.53
     gu
    0.52
     GU
    0.50
     Guin
    0.48
    Guillermo
    0.47
    ishable
    0.47
     Guar
    0.46
    Activations Density 0.095%

    No Known Activations