© 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. 1-GEMMASCOPE-RES-16K
    11. 3721
    Prev
    Next
    INDEX
    Explanations

    instances of the word "concern" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 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
    自立
    -0.49
    WriteAttribute
    -0.48
     sempurna
    -0.48
     autrement
    -0.48
     payé
    -0.48
    ΡΟ
    -0.47
     âgées
    -0.47
    uresti
    -0.47
     mulus
    -0.47
     ladr
    -0.46
    POSITIVE LOGITS
     concern
    3.39
     Concern
    3.06
    concern
    3.04
     concerns
    2.90
     CONCERN
    2.84
    Concern
    2.75
     Concerns
    2.63
    concerns
    2.58
     concerned
    2.56
    concerned
    2.29
    Activations Density 0.058%

    No Known Activations