© 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. 8-GEMMASCOPE-RES-16K
    11. 7582
    Prev
    Next
    INDEX
    Explanations

    instances of bias and corruption in political or judicial contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     StringTokenizer
    -0.65
    centralwidget
    -0.63
    exitRule
    -0.61
    complexContent
    -0.58
     debout
    -0.57
     Cataloging
    -0.57
    קישורים
    -0.56
    SequentialGroup
    -0.56
    CreateModel
    -0.55
    publicPath
    -0.53
    POSITIVE LOGITS
     bias
    0.71
     biased
    0.69
     <=",
    0.58
    biased
    0.56
     sway
    0.56
     favor
    0.56
    BIAS
    0.55
     bribe
    0.54
     Bias
    0.53
     biases
    0.53
    Activations Density 0.513%

    No Known Activations