Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 15041
    Prev
    Next
    INDEX
    Explanations

    quantitative phrases indicating amounts or numerical data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للمعارف
    -0.97
    Portale
    -0.69
    出版年
    -0.69
     EconPapers
    -0.66
    <bos>
    -0.65
    PhysRev
    -0.65
     Meksiku
    -0.65
     بيها
    -0.63
    Jereo
    -0.63
     Chwiliwch
    -0.63
    POSITIVE LOGITS
     six
    0.95
     three
    0.92
     four
    0.92
     five
    0.91
     eight
    0.84
     seven
    0.83
     nine
    0.78
     two
    0.77
     twelve
    0.66
     ten
    0.65
    Activations Density 0.309%

    No Known Activations