© 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. 8-GEMMASCOPE-RES-16K
    11. 5338
    Prev
    Next
    INDEX
    Explanations

    phrases related to rejection or denial of claims or arguments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyProduct
    -0.61
     up
    -0.55
     ens
    -0.54
    └
    -0.53
    Autowired
    -0.53
    ึ้น
    -0.53
     ढ
    -0.53
    artament
    -0.52
     образом
    -0.52
     du
    -0.52
    POSITIVE LOGITS
     rejection
    1.47
     Reject
    1.47
     reject
    1.46
     rejects
    1.46
     Rejection
    1.45
     rejecting
    1.38
     Refuse
    1.31
     denies
    1.31
     rejected
    1.29
     Rejected
    1.28
    Activations Density 0.247%

    No Known Activations