© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 12270
    Prev
    Next
    INDEX
    Explanations

    phrases related to racism and its implications in social and political contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 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
    NameInMap
    -0.64
    ırken
    -0.58
     nakalista
    -0.56
    __*/
    -0.49
    ásban
    -0.47
     дописавши
    -0.46
    msgTypes
    -0.45
     мәкал
    -0.45
     Paglinawan
    -0.45
    Kini
    -0.43
    POSITIVE LOGITS
     Period
    2.24
     period
    2.16
    Period
    2.00
    period
    1.98
     PERIOD
    1.97
    PERIOD
    1.72
     plain
    1.57
     periods
    1.41
    periods
    1.31
     Plain
    1.29
    Activations Density 0.365%

    No Known Activations