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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 9903
    Prev
    Next
    INDEX
    Explanations

    quotations and emphasized statements within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     ویکی‌پدیای
    -0.72
     препратки
    -0.71
    AccessFile
    -0.66
     estekak
    -0.66
    Autoritní
    -0.65
     مرئيه
    -0.60
    UserScript
    -0.60
     etc
    -0.60
     незавершена
    -0.59
     Например
    -0.58
    POSITIVE LOGITS
    Whilst
    0.60
     Whilst
    0.54
    发表于
    0.52
    OwnProperty
    0.51
    iastes
    0.50
    Alongside
    0.45
    Equ
    0.45
    itext
    0.45
     £
    0.45
    ########.
    0.43
    Activations Density 0.175%

    No Known Activations