© 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-2-9B
    7. Residual Stream - 16k
    9. 38-GEMMASCOPE-RES-16K
    11. 7395
    Prev
    Next
    INDEX
    Explanations

    words that indicate racial or social injustice themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    false equivalence and blame-shifting rhetoric, particularly in politically charged discourse.

    oai_token-act-pair · claude-4-5-haikuTriggered by @areeb0102
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     consape
    -0.52
     IMHO
    -0.50
    可以说
    -0.46
    可以说是
    -0.46
     dürfte
    -0.46
    ครับ
    -0.45
     IMO
    -0.45
    かなり
    -0.43
     imo
    -0.42
    %@",
    -0.42
    POSITIVE LOGITS
     somehow
    1.32
     Somehow
    0.96
     magically
    0.96
     supposedly
    0.96
     яко
    0.93
     angeb
    0.88
    Somehow
    0.87
     supuestamente
    0.81
     irgendwie
    0.74
     miraculously
    0.73
    Activations Density 1.087%

    No Known Activations