© 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. 7-GEMMASCOPE-RES-16K
    11. 1240
    Prev
    Next
    INDEX
    Explanations

    terms indicating contrast or contradiction despite prevailing situations or expectations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zzleHttp
    -0.58
    tldr
    -0.49
     forKey
    -0.45
    reathe
    -0.45
    ilitary
    -0.45
     vuitton
    -0.44
     propOrder
    -0.43
    phosa
    -0.43
    ewoo
    -0.43
    agerie
    -0.43
    POSITIVE LOGITS
     Trotzdem
    1.22
     Dennoch
    1.12
     Nevertheless
    1.10
    Nevertheless
    1.08
     nevertheless
    1.04
     trotzdem
    1.04
     nonetheless
    1.02
     Nonetheless
    1.01
    anmoins
    0.97
    Trotz
    0.96
    Activations Density 0.146%

    No Known Activations