© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 2695
    Prev
    Next
    INDEX
    Explanations

    references to authors in academic citations

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

    "al" followed by a period or citation

    np_acts-logits-general · gemini-2.0-flash

    et al

    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
    taca
    -0.61
    ituri
    -0.55
    󠁢
    -0.55
    andu
    -0.53
    tita
    -0.52
    τισ
    -0.51
     stands
    -0.50
    твор
    -0.49
     adic
    -0.49
    stand
    -0.49
    POSITIVE LOGITS
     المعيارى
    0.88
    
    0.85
    脚注の使い方
    0.80
     CURIAM
    0.80
    CodedInputStream
    0.79
    VersionUID
    0.73
    providedIn
    0.68
    发表于
    0.67
     الحره
    0.65
    úgó
    0.65
    Activations Density 0.130%

    No Known Activations