© 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. 10-GEMMASCOPE-RES-16K
    11. 16271
    Prev
    Next
    INDEX
    Explanations

    references to societal blame and fault, particularly in relation to racial or cultural issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AxisAlignment
    -0.88
     lediglich
    -0.72
     tevens
    -0.72
     تضيفلها
    -0.70
    互联网档案馆
    -0.69
    ')],
    -0.68
     sought
    -0.67
    に対し
    -0.67
    >"+
    -0.66
     hinweg
    -0.66
    POSITIVE LOGITS
     stuff
    1.04
     fucking
    0.87
     scared
    0.83
     everybody
    0.82
     freaking
    0.81
     guys
    0.80
     scary
    0.80
     stupid
    0.80
     thing
    0.80
     freakin
    0.78
    Activations Density 0.866%

    No Known Activations