© 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. 8636
    Prev
    Next
    INDEX
    Explanations

    code snippets related to database queries and data retrieval functions

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

    MySQL database queries

    np_acts-logits-general · gemini-2.0-flash

    database queries and string matching

    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
    PerformLayout
    -0.80
    +#+#
    -0.79
     kasarigan
    -0.77
    脚注の使い方
    -0.76
     okuyayım
    -0.74
     الاطلاع
    -0.70
    帖最后由
    -0.65
     للمعارف
    -0.64
    tagHelperRunner
    -0.63
    Diwedd
    -0.63
    POSITIVE LOGITS
     real
    0.45
    ंदीखरीदारी
    0.44
    rhein
    0.43
     query
    0.43
     ca
    0.41
     perio
    0.41
    gand
    0.40
    單位
    0.40
     bomb
    0.39
    query
    0.39
    Activations Density 0.094%

    No Known Activations