© 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. 33-GEMMASCOPE-RES-16K
    11. 466
    Prev
    Next
    INDEX
    Explanations

    statements of contradiction or fallacy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personendaten
    -0.61
     Infórmanos
    -0.51
    TemporalType
    -0.48
    addCriterion
    -0.48
     PagesJaunes
    -0.47
    OuterAlt
    -0.45
    хьтан
    -0.45
    CompleteListener
    -0.45
     NSCoder
    -0.45
     مواليد
    -0.44
    POSITIVE LOGITS
     actually
    3.23
    actually
    2.89
     Actually
    2.77
    Actually
    2.72
     ACTUALLY
    2.25
     aslında
    2.19
    其實
    2.16
    其实
    2.08
    実は
    2.08
     sebenarnya
    2.06
    Activations Density 1.143%

    No Known Activations