© 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. 1-GEMMASCOPE-RES-16K
    11. 8639
    Prev
    Next
    INDEX
    Explanations

    references to vice or roles associated with authority

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     كومونز
    -0.59
    下载附件
    -0.59
    ardless
    -0.54
     BoxFit
    -0.54
     TestBed
    -0.52
    Datuak
    -0.52
    igslist
    -0.51
    XtraReports
    -0.50
    Архівовано
    -0.50
    LabelTagHelper
    -0.49
    POSITIVE LOGITS
    Vice
    0.77
     Vice
    0.74
     vice
    0.71
    en
    0.60
    vice
    0.57
    English
    0.55
     françaises
    0.52
     VICE
    0.50
     franceses
    0.49
     French
    0.49
    Activations Density 0.188%

    No Known Activations