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. 22-GEMMASCOPE-RES-16K
    6. 13105
    Prev
    Next
    INDEX
    Explanations

    references to legal cases and judicial terms

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

    Tokens appearing before names or references

    np_acts-logits-general · gemini-2.0-flash

    names and legal citations

    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
    σιμοποι
    -0.51
    willReturn
    -0.47
    Comté
    -0.46
     selected
    -0.45
    htaccess
    -0.45
    지
    -0.44
     ujednoznacz
    -0.43
     sienta
    -0.43
    sobí
    -0.43
     nhan
    -0.43
    POSITIVE LOGITS
    httphttps
    0.76
    ViewFeatures
    0.72
     MainAxisSize
    0.70
     lenker
    0.69
    例句
    0.62
    はじめに
    0.58
     AUSTR
    0.58
    HomeAsUpEnabled
    0.57
    olescence
    0.57
    ISupport
    0.57
    Activations Density 0.095%

    No Known Activations