© 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. 35-GEMMASCOPE-RES-16K
    11. 14204
    Prev
    Next
    INDEX
    Explanations

    references to bias and its potential effects in research studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RegressionTest
    -0.56
     ModelExpression
    -0.49
     ComVisible
    -0.47
    \{\\
    -0.46
    ########.
    -0.45
     Mérimée
    -0.45
     Tight
    -0.45
    Према
    -0.44
     تضيفلها
    -0.43
    setObjectName
    -0.42
    POSITIVE LOGITS
     contamination
    0.85
     spurious
    0.82
     biases
    0.80
     confounding
    0.80
     bias
    0.78
     artifacts
    0.78
     inaccuracies
    0.77
     artefacts
    0.75
     noise
    0.71
     biais
    0.70
    Activations Density 3.122%

    No Known Activations