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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 15933
    Prev
    Next
    INDEX
    Explanations

    phrases related to social justice and inequality issues

    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
     its
    -2.02
    Its
    -1.76
     Its
    -1.74
    它的
    -1.48
     itself
    -1.47
    它
    -1.41
    its
    -1.35
     оно
    -1.27
     Оно
    -1.26
    itself
    -1.21
    POSITIVE LOGITS
     themselves
    1.79
    themselves
    1.59
     serem
    1.42
     were
    1.07
     are
    1.03
     которые
    0.99
     themſelves
    0.99
     lesquelles
    0.91
     nhau
    0.91
     których
    0.90
    Activations Density 1.786%

    No Known Activations