© 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-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 110128
    Prev
    Next
    INDEX
    Explanations

    words associated with bias and confusion in reasoning or evidence

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

    alleviates, obviates, prevents

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eterangan
    -0.39
     sommes
    -0.38
     kutumia
    -0.37
    koľvek
    -0.37
     memori
    -0.37
     contemp
    -0.37
     abandonado
    -0.37
    secuted
    -0.36
     surveyed
    -0.36
     menggunakan
    -0.36
    POSITIVE LOGITS
     helps
    0.83
     enables
    0.81
     brings
    0.80
     باعث
    0.80
     contributes
    0.79
     enhances
    0.74
     prevents
    0.71
     facilitates
    0.70
     enable
    0.69
     allows
    0.69
    Activations Density 0.046%

    No Known Activations