© 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. 21-GEMMASCOPE-RES-16K
    11. 7731
    Prev
    Next
    INDEX
    Explanations

    references to investigations and inquiries related to legal and governmental matters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Begriffsklä
    -0.52
    align
    -0.48
    脚注の使い方
    -0.48
    cipar
    -0.47
     ekst
    -0.46
    הערות
    -0.44
     actionPerformed
    -0.42
    Edy
    -0.41
    uxxxx
    -0.41
    abestanden
    -0.39
    POSITIVE LOGITS
     investigation
    2.45
     investigations
    2.19
     investigating
    2.11
    investigation
    2.10
     Investigation
    2.05
     investigate
    2.02
    Investigation
    1.97
    investig
    1.97
     investigates
    1.93
     INVESTIGATION
    1.90
    Activations Density 0.392%

    No Known Activations