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. 13-GEMMASCOPE-RES-16K
    6. 16184
    Prev
    Next
    INDEX
    Explanations

    discussions related to racial identity and historical grievances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AsUp
    -0.53
     Wikispecies
    -0.47
    testify
    -0.46
    hmig
    -0.45
    LayoutStyle
    -0.45
    __":
    -0.45
    JsonFormat
    -0.45
    WriteTagHelper
    -0.44
    Open
    -0.44
    accessible
    -0.43
    POSITIVE LOGITS
     stereotype
    0.73
     reputation
    0.68
     stereotyp
    0.64
    OGND
    0.59
     tainted
    0.56
    InitVars
    0.54
     réputation
    0.54
    例句
    0.54
     stereotypes
    0.54
     reputations
    0.53
    Activations Density 0.293%

    No Known Activations