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-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 7608
    Prev
    Next
    INDEX
    Explanations

    key terms associated with disruptions caused by major events, particularly focusing on the impact of COVID-19

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 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
    不通
    -0.47
     ब्रेकडाउन
    -0.41
     Miz
    -0.41
    WithIdentifier
    -0.40
     Lim
    -0.40
    LIM
    -0.40
    verschluss
    -0.39
     LIM
    -0.39
    ValueStyle
    -0.38
    Tikang
    -0.37
    POSITIVE LOGITS
    bootstrapcdn
    0.48
    ngdoc
    0.48
     BrowserModule
    0.45
    OGND
    0.44
     beginnetje
    0.44
    tgz
    0.43
     kasarigan
    0.40
     defaultstate
    0.40
    สง
    0.39
    :][
    0.39
    Activations Density 0.060%

    No Known Activations