© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 17-GEMMASCOPE-RES-16K
    6. 131
    Prev
    Next
    INDEX
    Explanations

    the presence of numerical data or statistical information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ี้ย
    -0.39
    pry
    -0.38
     Slide
    -0.38
     thoại
    -0.37
    ↵
    -0.37
     cheapest
    -0.37
     after
    -0.36
    ubel
    -0.36
    发表于
    -0.36
     such
    -0.36
    POSITIVE LOGITS
    featureID
    0.83
     հղումներ
    0.80
    batore
    0.80
     Efq
    0.79
     चीज़ों
    0.79
    onAttach
    0.78
    IsMutable
    0.77
     تضيفلها
    0.77
     EconPapers
    0.76
    Controllo
    0.76
    Activations Density 0.450%

    No Known Activations