© 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. 20-GEMMASCOPE-RES-16K
    11. 7777
    Prev
    Next
    INDEX
    Explanations

    URLs and numerical identifiers typically associated with academic references or publications

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

    Follows "8" after formatting

    np_acts-logits-general · gemini-2.0-flash

    978

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     odkazy
    -0.58
     viewDidLoad
    -0.55
    pyplot
    -0.54
    ImageContext
    -0.53
    wiek
    -0.53
    ThroughAttribute
    -0.52
    商品説明
    -0.52
    Билгалдахарш
    -0.51
    __(/*!
    -0.51
    Chham
    -0.50
    POSITIVE LOGITS
     Efq
    0.55
    thâu
    0.54
     jScrollPane
    0.52
    menea
    0.51
    orative
    0.50
     bezeichneter
    0.50
     ARXIV
    0.49
    "]="
    0.49
     priori
    0.49
    SharedDtor
    0.49
    Activations Density 0.091%

    No Known Activations