© 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. 20-GEMMASCOPE-RES-16K
    11. 4747
    Prev
    Next
    INDEX
    Explanations

    references to false statements or misleading claims in political contexts

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

    statements about falsehoods, lying, or misrepresentation.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     plan
    -0.37
     ready
    -0.36
    df
    -0.36
     du
    -0.33
     portfolio
    -0.33
     Hend
    -0.33
     $
    -0.31
     PROGRESS
    -0.31
     Web
    -0.31
     group
    -0.30
    POSITIVE LOGITS
    aarrggbb
    0.82
     falsehood
    0.74
     accuracy
    0.71
     inaccuracies
    0.68
     truthful
    0.68
     Accuracy
    0.68
     inaccurate
    0.66
     inaccuracy
    0.66
     veracity
    0.64
     truths
    0.62
    Activations Density 0.436%

    No Known Activations