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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 12375
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to machinery and engineering processes

    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
     spite
    -0.78
    idosis
    -0.66
    しまいました
    -0.66
    despite
    -0.65
    theless
    -0.65
    TagHelper
    -0.63
    withstanding
    -0.63
     क्यों
    -0.62
     astray
    -0.62
     despite
    -0.62
    POSITIVE LOGITS
     then
    1.00
    Then
    0.84
     então
    0.81
     Then
    0.78
     entweder
    0.78
     either
    0.77
    then
    0.74
     kemudian
    0.72
     następnie
    0.71
    either
    0.70
    Activations Density 1.098%

    No Known Activations