© 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. 6309
    Prev
    Next
    INDEX
    Explanations

    structured and informative content related to educational services

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

    advice or caution

    np_acts-logits-general · gemini-2.0-flash

    watchful whilst, enables corporations, prevent any

    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
     ویکی‌پدیا
    -0.82
     propOrder
    -0.82
    脚注の使い方
    -0.71
    principalTable
    -0.69
     للمعارف
    -0.63
     passés
    -0.62
    MemoryWarning
    -0.60
     <=",
    -0.59
     conci
    -0.59
     فريبيس
    -0.58
    POSITIVE LOGITS
     additionally
    0.97
     asimismo
    0.87
     nevertheless
    0.86
     ought
    0.85
     nonetheless
    0.84
     furthermore
    0.81
     likewise
    0.78
     utilized
    0.75
     observe
    0.73
     obtainable
    0.72
    Activations Density 0.633%

    No Known Activations