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 - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 73556
    Prev
    Next
    INDEX
    Explanations

    references to legal matters and ownership related to Michael Jackson and his estate

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     kasarigan
    -0.62
     CreateTagHelper
    -0.47
    ViewFeatures
    -0.46
    canestro
    -0.43
    XPATH
    -0.42
    NOPQRST
    -0.42
     näky
    -0.42
    ixote
    -0.42
     heureuse
    -0.42
     stř
    -0.41
    POSITIVE LOGITS
     posthum
    0.52
    cyklopedia
    0.47
    راث
    0.42
    webElementGuid
    0.42
    eadilan
    0.38
    ioutil
    0.37
    Continue
    0.36
    遺
    0.36
     насле
    0.36
     widow
    0.35
    Activations Density 0.077%

    No Known Activations